Articles | Volume 11, issue 1
https://doi.org/10.5194/soil-11-287-2025
© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/soil-11-287-2025
© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Original research article
| 
08 Apr 2025
Original research article |
| 08 Apr 2025
| 08 Apr 2025
Mapping near-real-time soil moisture dynamics over Tasmania with transfer learning
Marliana Tri Widyastuti
CORRESPONDING AUTHOR
School of Life and Environmental Sciences & Sydney Institute of Agriculture, The University of Sydney, Sydney, New South Wales, Australia
José Padarian
School of Life and Environmental Sciences & Sydney Institute of Agriculture, The University of Sydney, Sydney, New South Wales, Australia
Budiman Minasny
School of Life and Environmental Sciences & Sydney Institute of Agriculture, The University of Sydney, Sydney, New South Wales, Australia
Mathew Webb
Department of Natural Resources and Environment Tasmania, Prospect, Tasmania, Australia
Muh Taufik
Department of Geophysics and Meteorology, IPB University, Jalan Meranti Wing 19 Level 4 Darmaga Campus, Bogor, 16680, Indonesia
Darren Kidd
Department of Natural Resources and Environment Tasmania, Prospect, Tasmania, Australia
Related authors
Marliana Tri Widyastuti, Budiman Minasny, José Padarian, Federico Maggi, Matt Aitkenhead, Amélie Beucher, John Connolly, Dian Fiantis, Darren Kidd, Yuxin Ma, Fraser Macfarlane, Ciaran Robb, Rudiyanto, Budi Indra Setiawan, and Muh Taufik
Earth Syst. Sci. Data Discuss., https://doi.org/10.5194/essd-2024-333, https://doi.org/10.5194/essd-2024-333, 2024
Revised manuscript not accepted
Short summary
Short summary
PEATGRIDS, the first dataset containing maps of global peat thickness and carbon stock at 1 km resolution. The dataset has been publicly available at Zenodo to support further analyses and modelling of peatlands across the globe. This work employed the random forest machine learning model to provide spatially explicit peat carbon stock at pixel basis.
Yin-Chung Huang, José Padarian, Budiman Minasny, and Alex B. McBratney
EGUsphere, https://doi.org/10.5194/egusphere-2024-3703, https://doi.org/10.5194/egusphere-2024-3703, 2025
Short summary
Short summary
Uncertainty quantification plays a crucial role in reporting machine learning models in soil spectroscopy. This study introduces Monte Carlo conformal prediction (MC-CP), a novel method for uncertainty quantification in deep learning soil spectral models. MC-CP outperformed two established methods, providing the most reliable results. Its efficiency and robustness make it a practical choice for implementing soil spectral models in decision-making.
Marliana Tri Widyastuti, Budiman Minasny, José Padarian, Federico Maggi, Matt Aitkenhead, Amélie Beucher, John Connolly, Dian Fiantis, Darren Kidd, Yuxin Ma, Fraser Macfarlane, Ciaran Robb, Rudiyanto, Budi Indra Setiawan, and Muh Taufik
Earth Syst. Sci. Data Discuss., https://doi.org/10.5194/essd-2024-333, https://doi.org/10.5194/essd-2024-333, 2024
Revised manuscript not accepted
Short summary
Short summary
PEATGRIDS, the first dataset containing maps of global peat thickness and carbon stock at 1 km resolution. The dataset has been publicly available at Zenodo to support further analyses and modelling of peatlands across the globe. This work employed the random forest machine learning model to provide spatially explicit peat carbon stock at pixel basis.
Tobias Karl David Weber, Lutz Weihermüller, Attila Nemes, Michel Bechtold, Aurore Degré, Efstathios Diamantopoulos, Simone Fatichi, Vilim Filipović, Surya Gupta, Tobias L. Hohenbrink, Daniel R. Hirmas, Conrad Jackisch, Quirijn de Jong van Lier, John Koestel, Peter Lehmann, Toby R. Marthews, Budiman Minasny, Holger Pagel, Martine van der Ploeg, Shahab Aldin Shojaeezadeh, Simon Fiil Svane, Brigitta Szabó, Harry Vereecken, Anne Verhoef, Michael Young, Yijian Zeng, Yonggen Zhang, and Sara Bonetti
Hydrol. Earth Syst. Sci., 28, 3391–3433, https://doi.org/10.5194/hess-28-3391-2024, https://doi.org/10.5194/hess-28-3391-2024, 2024
Short summary
Short summary
Pedotransfer functions (PTFs) are used to predict parameters of models describing the hydraulic properties of soils. The appropriateness of these predictions critically relies on the nature of the datasets for training the PTFs and the physical comprehensiveness of the models. This roadmap paper is addressed to PTF developers and users and critically reflects the utility and future of PTFs. To this end, we present a manifesto aiming at a paradigm shift in PTF research.
Frisa Irawan Ginting, Rudiyanto Rudiyanto, Fatchurahman, Ramisah Mohd Shah, Norhidayah Che Soh, Sunny Goh Eng Giap, Dian Fiantis, Budi Indra Setiawan, Sam Schiller, Aaron Davitt, and Budiman Minasny
Earth Syst. Sci. Data Discuss., https://doi.org/10.5194/essd-2024-90, https://doi.org/10.5194/essd-2024-90, 2024
Preprint withdrawn
Short summary
Short summary
This study is the first to map rice cropping intensity and the harvested area across Southeast Asia at a spatial resolution of 10 m (SEA-Rice-Ci10). We have developed a geospatial inventory of paddy rice parcels and rice cropping intensity by integrating Sentinel-1 and 2 time-series data in a framework called LUCK-PALM, based on local phenological expert interpretation. According to our best knowledge, it is the finest-resolution and most accurate database of paddy rice in Southeast Asia.
Wartini Ng, Budiman Minasny, Alex McBratney, Patrice de Caritat, and John Wilford
Earth Syst. Sci. Data, 15, 2465–2482, https://doi.org/10.5194/essd-15-2465-2023, https://doi.org/10.5194/essd-15-2465-2023, 2023
Short summary
Short summary
With a higher demand for lithium (Li), a better understanding of its concentration and spatial distribution is important to delineate potential anomalous areas. This study uses a framework that combines data from recent geochemical surveys and relevant environmental factors to predict and map Li content across Australia. The map shows high Li concentration around existing mines and other potentially anomalous Li areas. The same mapping principles can potentially be applied to other elements.
Mercedes Román Dobarco, Alexandre M. J-C. Wadoux, Brendan Malone, Budiman Minasny, Alex B. McBratney, and Ross Searle
Biogeosciences, 20, 1559–1586, https://doi.org/10.5194/bg-20-1559-2023, https://doi.org/10.5194/bg-20-1559-2023, 2023
Short summary
Short summary
Soil organic carbon (SOC) is of a heterogeneous nature and varies in chemistry, stabilisation mechanisms, and persistence in soil. In this study we mapped the stocks of SOC fractions with different characteristics and turnover rates (presumably PyOC >= MAOC > POC) across Australia, combining spectroscopy and digital soil mapping. The SOC stocks (0–30 cm) were estimated as 13 Pg MAOC, 2 Pg POC, and 5 Pg PyOC.
José Padarian, Budiman Minasny, Alex B. McBratney, and Pete Smith
SOIL Discuss., https://doi.org/10.5194/soil-2021-73, https://doi.org/10.5194/soil-2021-73, 2021
Manuscript not accepted for further review
Short summary
Short summary
Soil organic carbon sequestration is considered an attractive technology to partially mitigate climate change. Here, we show how the SOC storage potential varies globally. The estimated additional SOC storage potential in the topsoil of global croplands (29–67 Pg C) equates to only 2 to 5 years of emissions offsetting and 32 % of agriculture's 92 Pg historical carbon debt. Since SOC is temperature-dependent, this potential is likely to reduce by 18 % by 2040 due to climate change.
Wartini Ng, Budiman Minasny, Wanderson de Sousa Mendes, and José Alexandre Melo Demattê
SOIL, 6, 565–578, https://doi.org/10.5194/soil-6-565-2020, https://doi.org/10.5194/soil-6-565-2020, 2020
Short summary
Short summary
The number of samples utilised to create predictive models affected model performance. This research compares the number of samples needed by a deep learning model to outperform the traditional machine learning models using visible near-infrared spectroscopy data for soil properties predictions. The deep learning model was found to outperform machine learning models when the sample size was above 2000.
José Padarian, Alex B. McBratney, and Budiman Minasny
SOIL, 6, 389–397, https://doi.org/10.5194/soil-6-389-2020, https://doi.org/10.5194/soil-6-389-2020, 2020
Short summary
Short summary
In this paper we introduce the use of game theory to interpret a digital soil mapping (DSM) model to understand the contribution of environmental factors to the prediction of soil organic carbon (SOC) in Chile. The analysis corroborated that the SOC model is capturing sensible relationships between SOC and climatic and topographical factors. We were able to represent them spatially (map) addressing the limitations of the current interpretation of models in DSM.
Yosra Ellili-Bargaoui, Brendan Philip Malone, Didier Michot, Budiman Minasny, Sébastien Vincent, Christian Walter, and Blandine Lemercier
SOIL, 6, 371–388, https://doi.org/10.5194/soil-6-371-2020, https://doi.org/10.5194/soil-6-371-2020, 2020
Sanjeewani Nimalka Somarathna Pallegedara Dewage, Budiman Minasny, and Brendan Malone
SOIL, 6, 359–369, https://doi.org/10.5194/soil-6-359-2020, https://doi.org/10.5194/soil-6-359-2020, 2020
Short summary
Short summary
Most soil management activities are implemented at farm scale, yet digital soil maps are commonly available at regional/national scales. This study proposes Bayesian area-to-point kriging to downscale regional-/national-scale soil property maps to farm scale. A regional soil carbon map with a resolution of 100 m (block support) was disaggregated to 10 m (point support) information for a farm in northern NSW, Australia. Results are presented with the uncertainty of the downscaling process.
José Padarian and Alex B. McBratney
SOIL, 6, 89–94, https://doi.org/10.5194/soil-6-89-2020, https://doi.org/10.5194/soil-6-89-2020, 2020
Short summary
Short summary
Data sharing and collaboration are critical to solving large-scale problems. The prevailing soil data-sharing model is of a centralized nature and, consequently, results in the participants ceding control and governance over their data to the lead party. Here we explore the use of a distributed ledger (blockchain) to solve the aforementioned issues. We also describe the potential use case of developing a global soil spectral library between multiple, international institutions.
José Padarian, Budiman Minasny, and Alex B. McBratney
SOIL, 6, 35–52, https://doi.org/10.5194/soil-6-35-2020, https://doi.org/10.5194/soil-6-35-2020, 2020
Short summary
Short summary
The application of machine learning (ML) has shown an accelerated adoption in soil sciences. It is a difficult task to manually review all papers on the application of ML. This paper aims to provide a review of the application of ML aided by topic modelling in order to find patterns in a large collection of publications. The objective is to gain insight into the applications and to discuss research gaps. We found 12 main topics and that ML methods usually perform better than traditional ones.
José Padarian and Ignacio Fuentes
SOIL, 5, 177–187, https://doi.org/10.5194/soil-5-177-2019, https://doi.org/10.5194/soil-5-177-2019, 2019
Short summary
Short summary
A large amount of descriptive information is available in geosciences. Considering the advances in natural language it is possible to
rescuethis information and transform it into a numerical form (embeddings). We used 280764 full-text scientific articles to train a language model capable of generating such embeddings. Our domain-specific embeddings (GeoVec) outperformed general domain embedding tasks such as analogies, relatedness, and categorisation, and can be used in novel applications.
Alexandre M. J.-C. Wadoux, José Padarian, and Budiman Minasny
SOIL, 5, 107–119, https://doi.org/10.5194/soil-5-107-2019, https://doi.org/10.5194/soil-5-107-2019, 2019
José Padarian, Budiman Minasny, and Alex B. McBratney
SOIL, 5, 79–89, https://doi.org/10.5194/soil-5-79-2019, https://doi.org/10.5194/soil-5-79-2019, 2019
Short summary
Short summary
Digital soil mapping has been widely used as a cost-effective method for generating soil maps. DSM models are usually calibrated using point observations and rarely incorporate contextual information of the landscape. Here, we use convolutional neural networks to incorporate spatial context. We used as input a 3-D stack of covariate images to simultaneously predict organic carbon content at multiple depths. In this study, our model reduced the error by 30 % compared with conventional techniques.
Related subject area
Soils and water
The effect of groundwater depth on topsoil organic matter mineralization during a simulated dry summer in northwestern Europe
Depth extrapolation of field-scale soil moisture time series derived with cosmic-ray neutron sensing (CRNS) using the soil moisture analytical relationship (SMAR) model
Addressing soil data needs and data gaps in catchment-scale environmental modelling: the European perspective
Optimized fertilization using online soil nitrate data
Intensive agricultural management-induced subsurface accumulation of water-extractable colloidal P in a Vertisol
Perspectives on the misconception of levitating soil aggregates
Combining lime and organic amendments based on titratable alkalinity for efficient amelioration of acidic soils
Sequestering carbon in the subsoil benefits crop transpiration at the onset of drought
Pesticide transport through the vadose zone under sugarcane in the Wet Tropics, Australia
Reproducibility of the wet part of the soil water retention curve: a European interlaboratory comparison
The higher relative concentration of K+ to Na+ in saline water improves soil hydraulic conductivity, salt-leaching efficiency and structural stability
Agricultural use of compost under different irrigation strategies in a hedgerow olive grove under Mediterranean conditions – a comparison with traditional systems
Potential of natural language processing for metadata extraction from environmental scientific publications
Soil and crop management practices and the water regulation functions of soils: a qualitative synthesis of meta-analyses relevant to European agriculture
Effects of innovative long-term soil and crop management on topsoil properties of a Mediterranean soil based on detailed water retention curves
Polyester microplastic fibers affect soil physical properties and erosion as a function of soil type
Modelling the effect of catena position and hydrology on soil chemical weathering
Long-term impact of cover crop and reduced disturbance tillage on soil pore size distribution and soil water storage
Effective hydraulic properties of 3D virtual stony soils identified by inverse modeling
Biochar alters hydraulic conductivity and impacts nutrient leaching in two agricultural soils
Impact of freeze–thaw cycles on soil structure and soil hydraulic properties
Added value of geophysics-based soil mapping in agro-ecosystem simulations
Particulate macronutrient exports from tropical African montane catchments point to the impoverishment of agricultural soils
A review of the global soil property maps for Earth system models
Saturated and unsaturated salt transport in peat from a constructed fen
Sensitivity analysis of point and parametric pedotransfer functions for estimating water retention of soils in Algeria
Water in the critical zone: soil, water and life from profile to planet
Deriving pedotransfer functions for soil quartz fraction in southern France from reverse modeling
Morphological dynamics of gully systems in the subhumid Ethiopian Highlands: the Debre Mawi watershed
Characterization of stony soils' hydraulic conductivity using laboratory and numerical experiments
Quantification of the impact of hydrology on agricultural production as a result of too dry, too wet or too saline conditions
Sediment concentration rating curves for a monsoonal climate: upper Blue Nile
Nonstationarity of the electrical resistivity and soil moisture relationship in a heterogeneous soil system: a case study
Interactions between organisms and parent materials of a constructed Technosol shape its hydrostructural properties
Potential effects of vinasse as a soil amendment to control runoff and soil loss
Quantification of the inevitable: the influence of soil macrofauna on soil water movement in rehabilitated open-cut mined lands
Coupled cellular automata for frozen soil processes
Astrid Françoys, Orly Mendoza, Junwei Hu, Pascal Boeckx, Wim Cornelis, Stefaan De Neve, and Steven Sleutel
SOIL, 11, 121–140, https://doi.org/10.5194/soil-11-121-2025, https://doi.org/10.5194/soil-11-121-2025, 2025
Short summary
Short summary
To assess the impact of the groundwater table (GWT) depth on soil moisture and C mineralization, we designed a laboratory setup using 200 cm undisturbed soil columns. Surprisingly, the moisture increase induced by a shallower GWT did not result in enhanced C mineralization. We presume this upward capillary moisture effect was offset by increased C mineralization upon rewetting, particularly noticeable in drier soils when capillary rise affected the topsoil to a lesser extent due to a deeper GWT.
Daniel Rasche, Theresa Blume, and Andreas Güntner
SOIL, 10, 655–677, https://doi.org/10.5194/soil-10-655-2024, https://doi.org/10.5194/soil-10-655-2024, 2024
Short summary
Short summary
Soil moisture measurements at the field scale are highly beneficial for numerous (soil) hydrological applications. Cosmic-ray neutron sensing (CRNS) allows for the non-invasive monitoring of field-scale soil moisture across several hectares but only for the first few tens of centimetres of the soil. In this study, we modify and test a simple modeling approach to extrapolate CRNS-derived surface soil moisture information down to 450 cm depth and compare calibrated and uncalibrated model results.
Brigitta Szabó, Piroska Kassai, Svajunas Plunge, Attila Nemes, Péter Braun, Michael Strauch, Felix Witing, János Mészáros, and Natalja Čerkasova
SOIL, 10, 587–617, https://doi.org/10.5194/soil-10-587-2024, https://doi.org/10.5194/soil-10-587-2024, 2024
Short summary
Short summary
This research introduces methods and tools for obtaining soil input data in European case studies for environmental models like SWAT+. With various available soil datasets and prediction methods, determining the most suitable is challenging. The study aims to (i) catalogue open-access datasets and prediction methods for Europe, (ii) demonstrate and quantify differences between prediction approaches, and (iii) offer a comprehensive workflow with open-source R codes for deriving missing soil data.
Yonatan Yekutiel, Yuval Rotem, Shlomi Arnon, and Ofer Dahan
SOIL, 10, 335–347, https://doi.org/10.5194/soil-10-335-2024, https://doi.org/10.5194/soil-10-335-2024, 2024
Short summary
Short summary
A new soil nitrate monitoring system that was installed in a cultivated field enabled us, for the first-time, to control nitrate concentration across the soil profile. Frequent adjustment of fertilizer and water application followed the actual dynamic variation in nitrate concentration across the soil profile. Hence, a significant reduction in fertilizer application was achieved while preserving optimal crop yield.
Shouhao Li, Shuiqing Chen, Shanshan Bai, Jinfang Tan, and Xiaoqian Jiang
SOIL, 10, 49–59, https://doi.org/10.5194/soil-10-49-2024, https://doi.org/10.5194/soil-10-49-2024, 2024
Short summary
Short summary
The distribution of water-extractable colloids with soil profiles of 0–120 cm was investigated in a Vertisol under high-intensity agricultural management. A large number of experimental data show that colloidal phosphorus plays an important role in apatite transport throughout the profile. Thus, it is crucial to consider the impact of colloidal P when predicting surface-to-subsurface P loss in Vertisols.
Gina Garland, John Koestel, Alice Johannes, Olivier Heller, Sebastian Doetterl, Dani Or, and Thomas Keller
SOIL, 10, 23–31, https://doi.org/10.5194/soil-10-23-2024, https://doi.org/10.5194/soil-10-23-2024, 2024
Short summary
Short summary
The concept of soil aggregates is hotly debated, leading to confusion about their function or relevancy to soil processes. We propose that the use of conceptual figures showing detached and isolated aggregates can be misleading and has contributed to this skepticism. Here, we conceptually illustrate how aggregates can form and dissipate within the context of undisturbed soils, highlighting the fact that aggregates do not necessarily need to have distinct physical boundaries.
Birhanu Iticha, Luke M. Mosley, and Petra Marschner
SOIL, 10, 33–47, https://doi.org/10.5194/soil-10-33-2024, https://doi.org/10.5194/soil-10-33-2024, 2024
Short summary
Short summary
Little effort has been made to develop methods to calculate the application rates of lime combined with organic amendments (OAs) needed to neutralise soil acidity and achieve the desired pH for plant growth. The previous approach of estimating appropriate lime and OA combinations based on field trials is time-consuming and costly. Hence, we developed and successfully validated a new method to calculate the amount of lime or OAs in combined applications required to ameliorate acidity.
Maria Eliza Turek, Attila Nemes, and Annelie Holzkämper
SOIL, 9, 545–560, https://doi.org/10.5194/soil-9-545-2023, https://doi.org/10.5194/soil-9-545-2023, 2023
Short summary
Short summary
In this study, we systematically evaluated prospective crop transpiration benefits of sequestering soil organic carbon (SOC) under current and future climatic conditions based on the model SWAP. We found that adding at least 2% SOC down to at least 65 cm depth could increase transpiration annually by almost 40 mm, which can play a role in mitigating drought impacts in rain-fed cropping. Beyond this threshold, additional crop transpiration benefits of sequestering SOC are only marginal.
Rezaul Karim, Lucy Reading, Les Dawes, Ofer Dahan, and Glynis Orr
SOIL, 9, 381–398, https://doi.org/10.5194/soil-9-381-2023, https://doi.org/10.5194/soil-9-381-2023, 2023
Short summary
Short summary
The study was performed using continuous measurement of temporal variations in soil saturation and of the concentration of pesticides along the vadose zone profile and underlying alluvial aquifers at sugarcane fields in the Wet Tropics of Australia. A vadose zone monitoring system was set up to enable the characterization of pesticide (non-PS II herbicides) migration with respect to pesticide application, sugarcane growing period, and, finally, rainwater infiltration.
Benjamin Guillaume, Hanane Aroui Boukbida, Gerben Bakker, Andrzej Bieganowski, Yves Brostaux, Wim Cornelis, Wolfgang Durner, Christian Hartmann, Bo V. Iversen, Mathieu Javaux, Joachim Ingwersen, Krzysztof Lamorski, Axel Lamparter, András Makó, Ana María Mingot Soriano, Ingmar Messing, Attila Nemes, Alexandre Pomes-Bordedebat, Martine van der Ploeg, Tobias Karl David Weber, Lutz Weihermüller, Joost Wellens, and Aurore Degré
SOIL, 9, 365–379, https://doi.org/10.5194/soil-9-365-2023, https://doi.org/10.5194/soil-9-365-2023, 2023
Short summary
Short summary
Measurements of soil water retention properties play an important role in a variety of societal issues that depend on soil water conditions. However, there is little concern about the consistency of these measurements between laboratories. We conducted an interlaboratory comparison to assess the reproducibility of the measurement of the soil water retention curve. Results highlight the need to harmonize and standardize procedures to improve the description of unsaturated processes in soils.
Sihui Yan, Tibin Zhang, Binbin Zhang, Tonggang Zhang, Yu Cheng, Chun Wang, Min Luo, Hao Feng, and Kadambot H. M. Siddique
SOIL, 9, 339–349, https://doi.org/10.5194/soil-9-339-2023, https://doi.org/10.5194/soil-9-339-2023, 2023
Short summary
Short summary
The paper provides some new information about the effects of different relative concentrations of K+ to Na+ at constant electrical conductivity (EC) on soil hydraulic conductivity, salt-leaching efficiency and pore size distribution. In addition to Ca2+ and Mg2+, K+ plays an important role in soil structure stability. These findings can provide a scientific basis and technical support for the sustainable use of saline water and control of soil quality deterioration.
Laura L. de Sosa, María José Martín-Palomo, Pedro Castro-Valdecantos, and Engracia Madejón
SOIL, 9, 325–338, https://doi.org/10.5194/soil-9-325-2023, https://doi.org/10.5194/soil-9-325-2023, 2023
Short summary
Short summary
Olive groves are subject to enormous pressure to meet the social demands of production. In this work, we assess how an additional source of organic carbon and an irrigation control can somehow palliate the effect of olive grove intensification by comparing olive groves under different management and tree densities. We observed that a reduced irrigation regimen in combination with compost from the oil industry's own waste was able to enhance soil fertility under a water conservation strategy.
Guillaume Blanchy, Lukas Albrecht, John Koestel, and Sarah Garré
SOIL, 9, 155–168, https://doi.org/10.5194/soil-9-155-2023, https://doi.org/10.5194/soil-9-155-2023, 2023
Short summary
Short summary
Adapting agricultural practices to future climatic conditions requires us to synthesize the effects of management practices on soil properties with respect to local soil and climate. We showcase different automated text-processing methods to identify topics, extract metadata for building a database and summarize findings from publication abstracts. While human intervention remains essential, these methods show great potential to support evidence synthesis from large numbers of publications.
Guillaume Blanchy, Gilberto Bragato, Claudia Di Bene, Nicholas Jarvis, Mats Larsbo, Katharina Meurer, and Sarah Garré
SOIL, 9, 1–20, https://doi.org/10.5194/soil-9-1-2023, https://doi.org/10.5194/soil-9-1-2023, 2023
Short summary
Short summary
European agriculture is vulnerable to weather extremes. Nevertheless, by choosing well how to manage their land, farmers can protect themselves against drought and peak rains. More than a thousand observations across Europe show that it is important to keep the soil covered with living plants, even in winter. A focus on a general reduction of traffic on agricultural land is more important than reducing tillage. Organic material needs to remain or be added on the field as much as possible.
Alaitz Aldaz-Lusarreta, Rafael Giménez, Miguel A. Campo-Bescós, Luis M. Arregui, and Iñigo Virto
SOIL, 8, 655–671, https://doi.org/10.5194/soil-8-655-2022, https://doi.org/10.5194/soil-8-655-2022, 2022
Short summary
Short summary
This study shows how an innovative soil and crop management including no-tillage, cover crops and organic amendments is able to improve the topsoil physical quality compared to conventional management for rainfed cereal cropping in a semi-arid Mediterranean area in Navarre (Spain).
Rosolino Ingraffia, Gaetano Amato, Vincenzo Bagarello, Francesco G. Carollo, Dario Giambalvo, Massimo Iovino, Anika Lehmann, Matthias C. Rillig, and Alfonso S. Frenda
SOIL, 8, 421–435, https://doi.org/10.5194/soil-8-421-2022, https://doi.org/10.5194/soil-8-421-2022, 2022
Short summary
Short summary
The presence of microplastics in soil environments has received increased attention, but little research exists on the effects on different soil types and soil water erosion. We performed two experiments on the effects of polyester microplastic fiber on soil properties, soil aggregation, and soil erosion in three agricultural soils. Results showed that polyester microplastic fibers affect the formation of new aggregates and soil erosion and that such effects are strongly dependent on soil type.
Vanesa García-Gamero, Tom Vanwalleghem, Adolfo Peña, Andrea Román-Sánchez, and Peter A. Finke
SOIL, 8, 319–335, https://doi.org/10.5194/soil-8-319-2022, https://doi.org/10.5194/soil-8-319-2022, 2022
Short summary
Short summary
Short-scale soil variability has received much less attention than at the regional scale. The chemical depletion fraction (CDF), a proxy for chemical weathering, was measured and simulated with SoilGen along two opposite slopes in southern Spain. The results show that differences in CDF could not be explained by topography alone but by hydrological parameters. The model sensitivity test shows the maximum CDF value for intermediate precipitation has similar findings to other soil properties.
Samuel N. Araya, Jeffrey P. Mitchell, Jan W. Hopmans, and Teamrat A. Ghezzehei
SOIL, 8, 177–198, https://doi.org/10.5194/soil-8-177-2022, https://doi.org/10.5194/soil-8-177-2022, 2022
Short summary
Short summary
We studied the long-term effects of no-till (NT) and winter cover cropping (CC) practices on soil hydraulic properties. We measured soil water retention and conductivity and also conducted numerical simulations to compare soil water storage abilities under the different systems. Soils under NT and CC practices had improved soil structure. Conservation agriculture practices showed marginal improvement with respect to infiltration rates and water storage.
Mahyar Naseri, Sascha C. Iden, and Wolfgang Durner
SOIL, 8, 99–112, https://doi.org/10.5194/soil-8-99-2022, https://doi.org/10.5194/soil-8-99-2022, 2022
Short summary
Short summary
We simulated stony soils with low to high volumes of rock fragments in 3D using evaporation and multistep unit-gradient experiments. Hydraulic properties of virtual stony soils were identified under a wide range of soil matric potentials. The developed models for scaling the hydraulic conductivity of stony soils were evaluated under unsaturated flow conditions.
Danielle L. Gelardi, Irfan H. Ainuddin, Devin A. Rippner, Janis E. Patiño, Majdi Abou Najm, and Sanjai J. Parikh
SOIL, 7, 811–825, https://doi.org/10.5194/soil-7-811-2021, https://doi.org/10.5194/soil-7-811-2021, 2021
Short summary
Short summary
Biochar is purported to alter soil water dynamics and reduce nutrient loss when added to soils, though the mechanisms are often unexplored. We studied the ability of seven biochars to alter the soil chemical and physical environment. The flow of ammonium through biochar-amended soil was determined to be controlled through chemical affinity, and nitrate, to a lesser extent, through physical entrapment. These data will assist land managers in choosing biochars for specific agricultural outcomes.
Frederic Leuther and Steffen Schlüter
SOIL, 7, 179–191, https://doi.org/10.5194/soil-7-179-2021, https://doi.org/10.5194/soil-7-179-2021, 2021
Short summary
Short summary
Freezing and thawing cycles are an important agent of soil structural transformation during the winter season in the mid-latitudes. This study shows that it promotes a well-connected pore system, fragments dense soil clods, and, hence, increases the unsaturated conductivity by a factor of 3. The results are important for predicting the structure formation and hydraulic properties of soils, with the prospect of milder winters due to climate change, and for farmers preparing the seedbed in spring.
Cosimo Brogi, Johan A. Huisman, Lutz Weihermüller, Michael Herbst, and Harry Vereecken
SOIL, 7, 125–143, https://doi.org/10.5194/soil-7-125-2021, https://doi.org/10.5194/soil-7-125-2021, 2021
Short summary
Short summary
There is a need in agriculture for detailed soil maps that carry quantitative information. Geophysics-based soil maps have the potential to deliver such products, but their added value has not been fully investigated yet. In this study, we compare the use of a geophysics-based soil map with the use of two commonly available maps as input for crop growth simulations. The geophysics-based product results in better simulations, with improvements that depend on precipitation, soil, and crop type.
Jaqueline Stenfert Kroese, John N. Quinton, Suzanne R. Jacobs, Lutz Breuer, and Mariana C. Rufino
SOIL, 7, 53–70, https://doi.org/10.5194/soil-7-53-2021, https://doi.org/10.5194/soil-7-53-2021, 2021
Short summary
Short summary
Particulate macronutrient concentrations were up to 3-fold higher in a natural forest catchment compared to fertilized agricultural catchments. Although the particulate macronutrient concentrations were lower in the smallholder agriculture catchment, because of higher sediment loads from that catchment, the total particulate macronutrient loads were higher. Land management practices should be focused on agricultural land to reduce the loss of soil carbon and nutrients to the stream.
Yongjiu Dai, Wei Shangguan, Nan Wei, Qinchuan Xin, Hua Yuan, Shupeng Zhang, Shaofeng Liu, Xingjie Lu, Dagang Wang, and Fapeng Yan
SOIL, 5, 137–158, https://doi.org/10.5194/soil-5-137-2019, https://doi.org/10.5194/soil-5-137-2019, 2019
Short summary
Short summary
Soil data are widely used in various Earth science fields. We reviewed soil property maps for Earth system models, which can also offer insights to soil data developers and users. Old soil datasets are often based on limited observations and have various uncertainties. Updated and comprehensive soil data are made available to the public and can benefit related research. Good-quality soil data are identified and suggestions on how to improve and use them are provided.
Reuven B. Simhayov, Tobias K. D. Weber, and Jonathan S. Price
SOIL, 4, 63–81, https://doi.org/10.5194/soil-4-63-2018, https://doi.org/10.5194/soil-4-63-2018, 2018
Short summary
Short summary
Lab experiments were performed to understand solute transport in peat from an experimental fen. Transport was analyzed under saturated and unsaturated conditions using NaCl (salt). We tested the applicability of a physical-based model which finds a wide consensus vs. alternative models. Evidence indicated that Cl transport can be explained using a simple transport model. Hence, use of the physical transport mechanism in peat should be evidence based and not automatically assumed.
Sami Touil, Aurore Degre, and Mohamed Nacer Chabaca
SOIL, 2, 647–657, https://doi.org/10.5194/soil-2-647-2016, https://doi.org/10.5194/soil-2-647-2016, 2016
M. J. Kirkby
SOIL, 2, 631–645, https://doi.org/10.5194/soil-2-631-2016, https://doi.org/10.5194/soil-2-631-2016, 2016
Short summary
Short summary
The review paper surveys the state of the art with respect to water in the critical zone, taking a broad view that concentrates on the global range of natural soils, identifying some areas of currently active research.
Jean-Christophe Calvet, Noureddine Fritz, Christine Berne, Bruno Piguet, William Maurel, and Catherine Meurey
SOIL, 2, 615–629, https://doi.org/10.5194/soil-2-615-2016, https://doi.org/10.5194/soil-2-615-2016, 2016
Short summary
Short summary
Soil thermal conductivity in wet conditions can be retrieved together with the soil quartz content using a reverse modelling technique based on sub-hourly soil temperature observations at three depths below the soil surface.
A pedotransfer function is proposed for quartz, for the considered region in France.
Gravels have a major impact on soil thermal conductivity, and omitting the soil organic matter information tends to enhance this impact.
Assefa D. Zegeye, Eddy J. Langendoen, Cathelijne R. Stoof, Seifu A. Tilahun, Dessalegn C. Dagnew, Fasikaw A. Zimale, Christian D. Guzman, Birru Yitaferu, and Tammo S. Steenhuis
SOIL, 2, 443–458, https://doi.org/10.5194/soil-2-443-2016, https://doi.org/10.5194/soil-2-443-2016, 2016
Short summary
Short summary
Gully erosion rehabilitation programs in the humid Ethiopian highlands have not been effective, because the gully formation process and its controlling factors are not well understood. In this manuscript, the severity of gully erosion (onsite and offsite effect), the most controlling factors (e.g., ground water elevation) for gully formation, and their arresting mechanisms are discussed in detail. Most data were collected from the detailed measurements of 13 representative gullies.
Eléonore Beckers, Mathieu Pichault, Wanwisa Pansak, Aurore Degré, and Sarah Garré
SOIL, 2, 421–431, https://doi.org/10.5194/soil-2-421-2016, https://doi.org/10.5194/soil-2-421-2016, 2016
Short summary
Short summary
Determining the behaviour of stony soils with respect to infiltration and storage of water is of major importance, since stony soils are widespread across the globe. The most common procedure to overcome this difficulty is to describe the hydraulic characteristics of a stony soils in terms of the fine fraction of soil corrected for the volume of stones present. Our study suggests that considering this hypothesis might be ill-founded, especially for saturated soils.
Mirjam J. D. Hack-ten Broeke, Joop G. Kroes, Ruud P. Bartholomeus, Jos C. van Dam, Allard J. W. de Wit, Iwan Supit, Dennis J. J. Walvoort, P. Jan T. van Bakel, and Rob Ruijtenberg
SOIL, 2, 391–402, https://doi.org/10.5194/soil-2-391-2016, https://doi.org/10.5194/soil-2-391-2016, 2016
Short summary
Short summary
For calculating the effects of hydrological measures on agricultural production in the Netherlands a new comprehensive and climate proof method is being developed: WaterVision Agriculture (in Dutch: Waterwijzer Landbouw). End users have asked for a method that considers current and future climate, which can quantify the differences between years and also the effects of extreme weather events.
Mamaru A. Moges, Fasikaw A. Zemale, Muluken L. Alemu, Getaneh K. Ayele, Dessalegn C. Dagnew, Seifu A. Tilahun, and Tammo S. Steenhuis
SOIL, 2, 337–349, https://doi.org/10.5194/soil-2-337-2016, https://doi.org/10.5194/soil-2-337-2016, 2016
Short summary
Short summary
In tropical monsoonal Africa, sediment concentration data in rivers are lacking. Using occasional historically observed sediment loads, we developed a simple method for prediction sediment concentrations. Unlike previous methods, our techniques take into account that sediment concentrations decrease with the progression of the monsoon rains. With more testing, the developed method could improve sediment predictions in monsoonal climates.
Didier Michot, Zahra Thomas, and Issifou Adam
SOIL, 2, 241–255, https://doi.org/10.5194/soil-2-241-2016, https://doi.org/10.5194/soil-2-241-2016, 2016
Short summary
Short summary
This study focuses on temporal and spatial soil moisture changes along a toposequence crossed by a hedgerow, using ERT and occasional measurements. We found that the relationship between ER and soil moisture had two behaviors depending on soil heterogeneities. ER values were consistent with occasional measurements outside the root zone. The shift in this relationship was controlled by root system density and a particular topographical context in the proximity of the hedgerow.
Maha Deeb, Michel Grimaldi, Thomas Z. Lerch, Anne Pando, Agnès Gigon, and Manuel Blouin
SOIL, 2, 163–174, https://doi.org/10.5194/soil-2-163-2016, https://doi.org/10.5194/soil-2-163-2016, 2016
Short summary
Short summary
This paper addresses the evolution of engineered soils (i.e., Technosols). The formation of such soils begins with proportional mixing of urban waste. Technosols are particularly well suited for investigating the role of organisms in soil function development. This is because they provide a controlled environment where the soil development can be monitored over time.
Organisms and their interaction with parent materials positively affect the structure of Technosols.
Z. Hazbavi and S. H. R. Sadeghi
SOIL, 2, 71–78, https://doi.org/10.5194/soil-2-71-2016, https://doi.org/10.5194/soil-2-71-2016, 2016
Short summary
Short summary
This study evaluates the influences of vinasse waste of sugarcane industries on runoff and soil loss at small plot scale. Laboratory results indicated that the vinasse at different levels could not significantly (P > 0.05) decrease the runoff amounts and soil loss rates in the study plots compared to untreated plots. The average amounts of minimum runoff volume and soil loss were about 3985 mL and 46 g for the study plot at a 1 L m−2 level of vinasse application.
S. Arnold and E. R. Williams
SOIL, 2, 41–48, https://doi.org/10.5194/soil-2-41-2016, https://doi.org/10.5194/soil-2-41-2016, 2016
Short summary
Short summary
Soil water models are used to design cover systems for containing hazardous waste following mining. Often, soil invertebrates are omitted from these calculations, despite playing a major role in soil development (nutrient cycling) and water pathways (seepage, infiltration). As such, soil invertebrates can influence the success of waste cover systems. We propose that experiments in glasshouses, laboratories and field trials on mined lands be undertaken to provide knowledge for these models.
R. M. Nagare, P. Bhattacharya, J. Khanna, and R. A. Schincariol
SOIL, 1, 103–116, https://doi.org/10.5194/soil-1-103-2015, https://doi.org/10.5194/soil-1-103-2015, 2015
Cited articles
Aas, K., Jullum, M., and Løland, A.: Explaining individual predictions when features are dependent: More accurate approximations to Shapley values, Artif. Intell., 298, 103502, https://doi.org/10.1016/j.artint.2021.103502, 2021.
Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G. S., Davis, A., Dean, J., and Devin, M.: TensorFlow: Large-scale machine learning on heterogeneous systems, arXiv [preprint], https://doi.org/10.48550/arXiv.1603.04467, 2015.
Alemohammad, S. H., Kolassa, J., Prigent, C., Aires, F., and Gentine, P.: Global downscaling of remotely sensed soil moisture using neural networks, Hydrol. Earth Syst. Sci., 22, 5341–5356, https://doi.org/10.5194/hess-22-5341-2018, 2018.
Behrens, T., Schmidt, K., MacMillan, R. A., and Viscarra Rossel, R. A.: Multi-scale digital soil mapping with deep learning, Sci. Rep.-UK, 8, 15244, https://doi.org/10.1038/s41598-018-33516-6, 2018.
Beringer, J., Hutley, L. B., McHugh, I., Arndt, S. K., Campbell, D., Cleugh, H. A., Cleverly, J., Resco de Dios, V., Eamus, D., Evans, B., Ewenz, C., Grace, P., Griebel, A., Haverd, V., Hinko-Najera, N., Huete, A., Isaac, P., Kanniah, K., Leuning, R., Liddell, M. J., Macfarlane, C., Meyer, W., Moore, C., Pendall, E., Phillips, A., Phillips, R. L., Prober, S. M., Restrepo-Coupe, N., Rutledge, S., Schroder, I., Silberstein, R., Southall, P., Yee, M. S., Tapper, N. J., van Gorsel, E., Vote, C., Walker, J., and Wardlaw, T.: An introduction to the Australian and New Zealand flux tower network – OzFlux, Biogeosciences, 13, 5895–5916, https://doi.org/10.5194/bg-13-5895-2016, 2016.
Bishop, T. F. A., McBratney, A. B., and Laslett, G. M.: Modelling soil attribute depth functions with equal-area quadratic smoothing splines, Geoderma, 91, 27–45, https://doi.org/10.1016/S0016-7061(99)00003-8, 1999.
Cai, Y., Fan, P., Lang, S., Li, M., Muhammad, Y., and Liu, A.: Downscaling of SMAP Soil Moisture Data by Using a Deep Belief Network, Remote Sens.-Basel, 14, 5681, https://doi.org/10.3390/rs14225681, 2022.
Cotching, W. E.: Organic matter in the agricultural soils of Tasmania, Australia – A review, Geoderma, 312, 170–182, https://doi.org/10.1016/j.geoderma.2017.10.006, 2018.
Cotching, W. E., Lynch, S., and Kidd, D. B.: Dominant soil orders in Tasmania: Distribution and selected properties, Aust. J. Soil Res., 47, 537–548, https://doi.org/10.1071/SR08239, 2009.
Dashtian, H., Young, M. H., Young, B. E., McKinney, T., Rateb, A. M., Niyogi, D., and Kumar, S. V.: A framework to nowcast soil moisture with NASA SMAP level 4 data using in-situ measurements and deep learning, Journal of Hydrology: Regional Studies, 56, 102020, https://doi.org/10.1016/j.ejrh.2024.102020, 2024.
Datta, P. and Faroughi, S. A.: A multihead LSTM technique for prognostic prediction of soil moisture, Geoderma, 433, 116452, https://doi.org/10.1016/j.geoderma.2023.116452, 2023.
Department of Agriculture Fisheries and Forestry: Catchment Scale Land Use of Australia – Update December 2018, Department of Agriculture, Fisheries and Forestry [data set], https://www.agriculture.gov.au/abares/aclump/land-use/catchment-scale-land-use-of-australia-update-december-2018 (Last access: 28 August 2023), 2019.
Dorigo, W., Himmelbauer, I., Aberer, D., Schremmer, L., Petrakovic, I., Zappa, L., Preimesberger, W., Xaver, A., Annor, F., Ardö, J., Baldocchi, D., Bitelli, M., Blöschl, G., Bogena, H., Brocca, L., Calvet, J.-C., Camarero, J. J., Capello, G., Choi, M., Cosh, M. C., van de Giesen, N., Hajdu, I., Ikonen, J., Jensen, K. H., Kanniah, K. D., de Kat, I., Kirchengast, G., Kumar Rai, P., Kyrouac, J., Larson, K., Liu, S., Loew, A., Moghaddam, M., Martínez Fernández, J., Mattar Bader, C., Morbidelli, R., Musial, J. P., Osenga, E., Palecki, M. A., Pellarin, T., Petropoulos, G. P., Pfeil, I., Powers, J., Robock, A., Rüdiger, C., Rummel, U., Strobel, M., Su, Z., Sullivan, R., Tagesson, T., Varlagin, A., Vreugdenhil, M., Walker, J., Wen, J., Wenger, F., Wigneron, J. P., Woods, M., Yang, K., Zeng, Y., Zhang, X., Zreda, M., Dietrich, S., Gruber, A., van Oevelen, P., Wagner, W., Scipal, K., Drusch, M., and Sabia, R.: The International Soil Moisture Network: serving Earth system science for over a decade, Hydrol. Earth Syst. Sci., 25, 5749–5804, https://doi.org/10.5194/hess-25-5749-2021, 2021.
Fang, K. and Shen, C.: Near-real-time forecast of satellite-based soil moisture using long short-term memory with an adaptive data integration kernel, J. Hydrometeorol., 21, 399–413, https://doi.org/10.1175/JHM-D-19-0169.1, 2020.
Frost, A., Ramchurn, A., and Hafeez, M.: Evaluation of the Bureau's Operational AWRA-L Model, Melbourne, Bureau of Meteorology, 80 pp., https://awo.bom.gov.au/assets/notes/publications/Frost_Evaluation_Report.pdf (last access: 25 August 2023), 2016.
Fuentes, I., Padarian, J., and Vervoort, R. W.: Towards near real-time national-scale soil water content monitoring using data fusion as a downscaling alternative, J. Hydrol., 609, 127705, https://doi.org/10.1016/j.jhydrol.2022.127705, 2022.
Gütter, J., Kruspe, A., Zhu, X. X., and Niebling, J.: Impact of Training Set Size on the Ability of Deep Neural Networks to Deal with Omission Noise, Front. Remote Sens., 3, 932431, https://doi.org/10.3389/frsen.2022.932431, 2022.
Han, H., Choi, C., Kim, J., Morrison, R. R., Jung, J., and Kim, H. S.: Multiple-Depth Soil Moisture Estimates Using Artificial Neural Network and Long Short-Term Memory Models, Water-Sui, 13, 2584, https://doi.org/10.3390/w13182584, 2021.
Hu, F., Wei, Z., Zhang, W., Dorjee, D., and Meng, L.: A spatial downscaling method for SMAP soil moisture through visible and shortwave-infrared remote sensing data, J. Hydrol., 590, 125360, https://doi.org/10.1016/j.jhydrol.2020.125360, 2020.
Huang, Y.: Advances in Artificial Neural Networks – Methodological Development and Application, Algorithms, 2, 973–1007, 2009.
Jarvis, A., Reuter, H. I., Nelson, A., and Guevara, E.: Hole-filled SRTM for the globe Version 4, available from the CGIAR-CSI SRTM 90 m Database, 2008.
Kidd, D., Webb, M., Malone, B., Minasny, B., and McBratney, A.: Eighty-metre resolution 3D soil-attribute maps for Tasmania, Australia, Soil Res., 53, 932–955, https://doi.org/10.1071/SR14268, 2015a.
Kidd, D., Webb, M., Malone, B., Minasny, B., and McBratney, A.: Digital soil assessment of agricultural suitability, versatility and capital in Tasmania, Australia, Geoderma Regional, 6, 7–21, https://doi.org/10.1016/j.geodrs.2015.08.005, 2015b.
Kidd, D. B., Malone, B. P., McBratney, A. B., Minasny, B., and Webb, M. A.: Digital mapping of a soil drainage index for irrigated enterprise suitability in Tasmania, Australia, Soil Res., 52, 107–119, https://doi.org/10.1071/SR13100, 2014.
Li, B., Rodell, M., Kumar, S., Beaudoing, H. K., Getirana, A., Zaitchik, B. F., de Goncalves, L. G., Cossetin, C., Bhanja, S., Mukherjee, A., Tian, S., Tangdamrongsub, N., Long, D., Nanteza, J., Lee, J., Policelli, F., Goni, I. B., Daira, D., Bila, M., de Lannoy, G., Mocko, D., Steele-Dunne, S. C., Save, H., and Bettadpur, S.: Global GRACE Data Assimilation for Groundwater and Drought Monitoring: Advances and Challenges, Water Resour. Res., 55, 7564–7586, https://doi.org/10.1029/2018WR024618, 2019.
Li, Q., Wang, Z., Shangguan, W., Li, L., Yao, Y., and Yu, F.: Improved daily SMAP satellite soil moisture prediction over China using deep learning model with transfer learning, J. Hydrol., 600, 126698, https://doi.org/10.1016/j.jhydrol.2021.126698, 2021.
Li, Q., Li, Z., Shangguan, W., Wang, X., Li, L., and Yu, F.: Improving soil moisture prediction using a novel encoder-decoder model with residual learning, Comput. Electron. Agr., 195, 106816, https://doi.org/10.1016/j.compag.2022.106816, 2022a.
Li, Q., Zhu, Y., Shangguan, W., Wang, X., Li, L., and Yu, F.: An attention-aware LSTM model for soil moisture and soil temperature prediction, Geoderma, 409, 115651, https://doi.org/10.1016/j.geoderma.2021.115651, 2022b.
Li, Q., Shi, G., Shangguan, W., Nourani, V., Li, J., Li, L., Huang, F., Zhang, Y., Wang, C., Wang, D., Qiu, J., Lu, X., and Dai, Y.: A 1 km daily soil moisture dataset over China using in situ measurement and machine learning, Earth Syst. Sci. Data, 14, 5267–5286, https://doi.org/10.5194/essd-14-5267-2022, 2022c.
Li, X., Zhu, Y., Li, Q., Zhao, H., Zhu, J., and Zhang, C.: Interpretable spatio-temporal modeling for soil temperature prediction, Front. Forests Global Change, 6, 1295731, https://doi.org/10.3389/ffgc.2023.1295731, 2023.
Lin, H., Yu, Z., Chen, X., Gu, H., Ju, Q., and Shen, T.: Spatial–temporal dynamics of meteorological and soil moisture drought on the Tibetan Plateau: Trend, response, and propagation process, J. Hydrol., 130211, https://doi.org/10.1016/j.jhydrol.2023.130211, 2023.
Lin, L. I. K.: A Concordance Correlation Coefficient to Evaluate Reproducibility, Biometrics, 45, 255–268, https://doi.org/10.2307/2532051, 1989.
Lindemann, B., Müller, T., Vietz, H., Jazdi, N., and Weyrich, M.: A survey on long short-term memory networks for time series prediction, Proc. CIRP, 99, 650–655, https://doi.org/10.1016/j.procir.2021.03.088, 2021.
Liu, J., Rahmani, F., Lawson, K., and Shen, C.: A Multiscale Deep Learning Model for Soil Moisture Integrating Satellite and In Situ Data, Geophys. Res. Lett., 49, e2021GL096847, https://doi.org/10.1029/2021GL096847, 2022.
Lu, J., Behbood, V., Hao, P., Zuo, H., Xue, S., and Zhang, G.: Transfer learning using computational intelligence: A survey, Knowl.-Based Syst., 80, 14–23, https://doi.org/10.1016/j.knosys.2015.01.010, 2015.
Lundberg, S. M. and Lee, S. I.: A unified approach to interpreting model predictions, arXiv [preprint], https://doi.org/10.48550/arXiv.1705.07874, 2017.
Malone, B. and Searle, R.: Soil and Landscape Grid National Soil Attribute Maps – Clay (3′′ resolution) – Release 2. v5., CSIRO [data set], https://doi.org/10.25919/hc4s-3130, 2022.
Minasny, B. and McBratney, A. B.: Integral energy as a measure of soil-water availability, Plant Soil, 249, 253–262, https://doi.org/10.1023/A:1022825732324, 2003.
Minasny, B., Bandai, T., Ghezzehei, T. A., Huang, Y.-C., Ma, Y., McBratney, A. B., Ng, W., Norouzi, S., Padarian, J., Rudiyanto, Sharififar, A., Styc, Q., and Widyastuti, M.: Soil Science-Informed Machine Learning, Geoderma, 452, 117094, https://doi.org/10.1016/j.geoderma.2024.117094, 2024.
Mohammadifar, A., Gholami, H., and Golzari, S.: Assessment of the uncertainty and interpretability of deep learning models for mapping soil salinity using DeepQuantreg and game theory, Sci. Rep.-UK, 12, 15167, https://doi.org/10.1038/s41598-022-19357-4, 2022.
Muñoz-Sabater, J., Dutra, E., Agustí-Panareda, A., Albergel, C., Arduini, G., Balsamo, G., Boussetta, S., Choulga, M., Harrigan, S., Hersbach, H., Martens, B., Miralles, D. G., Piles, M., Rodríguez-Fernández, N. J., Zsoter, E., Buontempo, C., and Thépaut, J.-N.: ERA5-Land: a state-of-the-art global reanalysis dataset for land applications, Earth Syst. Sci. Data, 13, 4349–4383, https://doi.org/10.5194/essd-13-4349-2021, 2021.
Ng, W., Minasny, B., Mendes, W. D. S., and Demattê, J. A. M.: The influence of training sample size on the accuracy of deep learning models for the prediction of soil properties with near-infrared spectroscopy data, SOIL, 6, 565–578, https://doi.org/10.5194/soil-6-565-2020, 2020.
Odebiri, O., Mutanga, O., and Odindi, J.: Deep learning-based national scale soil organic carbon mapping with Sentinel-3 data, Geoderma, 411, 115695, https://doi.org/10.1016/j.geoderma.2022.115695, 2022.
Padarian, J., Minasny, B., and McBratney, A. B.: Transfer learning to localise a continental soil vis-NIR calibration model, Geoderma, 340, 279–288, https://doi.org/10.1016/j.geoderma.2019.01.009, 2019a.
Padarian, J., Minasny, B., and McBratney, A. B.: Using deep learning for digital soil mapping, SOIL, 5, 79–89, https://doi.org/10.5194/soil-5-79-2019, 2019b.
Padarian, J., McBratney, A. B., and Minasny, B.: Game theory interpretation of digital soil mapping convolutional neural networks, SOIL, 6, 389–397, https://doi.org/10.5194/soil-6-389-2020, 2020.
Pan, S. J. and Yang, Q.: A Survey on Transfer Learning, IEEE T. Knowl. Data En., 22, 1345–1359, https://doi.org/10.1109/TKDE.2009.191, 2010.
Park, S.-H., Lee, B.-Y., Kim, M.-J., Sang, W., Seo, M. C., Baek, J.-K., Yang, J. E., and Mo, C.: Development of a Soil Moisture Prediction Model Based on Recurrent Neural Network Long Short-Term Memory (RNN-LSTM) in Soybean Cultivation, Sensors, 23, 1976, https://doi.org/10.3390/s23041976, 2023.
Park, Y. S. and Lek, S.: Chapter 7 – Artificial Neural Networks: Multilayer Perceptron for Ecological Modeling, in: Developments in Environmental Modelling, edited by: Jørgensen, S. E., Elsevier, 123–140, https://doi.org/10.1016/B978-0-444-63623-2.00007-4, 2016.
Reichle, R. H., De Lannoy, G. J. M., Liu, Q., Ardizzone, J. V., Colliander, A., Conaty, A., Crow, W., Jackson, T. J., Jones, L. A., Kimball, J. S., Koster, R. D., Mahanama, S. P., Smith, E. B., Berg, A., Bircher, S., Bosch, D., Caldwell, T. G., Cosh, M., González-Zamora, Á., Holifield Collins, C. D., Jensen, K. H., Livingston, S., Lopez-Baeza, E., Martínez-Fernández, J., McNairn, H., Moghaddam, M., Pacheco, A., Pellarin, T., Prueger, J., Rowlandson, T., Seyfried, M., Starks, P., Su, Z., Thibeault, M., van der Velde, R., Walker, J., Wu, X., and Zeng, Y.: Assessment of the SMAP Level-4 Surface and Root-Zone Soil Moisture Product Using In Situ Measurements, J. Hydrometeorol., 18, 2621–2645, https://doi.org/10.1175/JHM-D-17-0063.1, 2017.
Rumelhart, D. E., Hinton, G. E., and Williams, R. J.: Learning representations by back-propagating errors, Nature, 323, 533–536, 1986.
Searle, R., Somarathna, P. D. S. N., and Malone, B.: Soil and Landscape Grid National Soil Attribute Maps – Available Volumetric Water Capacity (Percent) (3 arc second resolution) Version 2. v3. (v2), CSIRO [data set], https://doi.org/10.25919/4jwj-na34, 2022.
Smith, A. B., Walker, J. P., Western, A. W., Young, R. I., Ellett, K. M., Pipunic, R. C., Grayson, R. B., Siriwardena, L., Chiew, F. H. S., and Richter, H.: The Murrumbidgee soil moisture monitoring network data set, Water Resour. Res., 48, W07701, https://doi.org/10.1029/2012WR011976, 2012.
Stenson, M., Searle, R., Malone, B., Sommer, A., Renzullo, L., and Di, H.: Australia wide daily volumetric soil moisture estimates (1.0), Terrestrial Ecosystem Research Network [data set], https://doi.org/10.25901/b020-nm39, 2021.
Sulla-Menashe, D. and Friedl, M. A.: MCD12Q1 MODIS/Terra+Aqua Land Cover Type Yearly L3 Global 500 m SIN Grid V061, USGS [data set], https://doi.org/10.5067/MODIS/MCD12Q1.061, 2021.
Taufik, M., Widyastuti, M. T., Sulaiman, A., Murdiyarso, D., Santikayasa, I. P., and Minasny, B.: An improved drought-fire assessment for managing fire risks in tropical peatlands, Agr. Forest Meteorol., 312, 108738, https://doi.org/10.1016/j.agrformet.2021.108738, 2022.
Teixeira, I., Morais, R., Sousa, J. J., and Cunha, A.: Deep Learning Models for the Classification of Crops in Aerial Imagery: A Review, Agriculture, 13, 13050965, https://doi.org/10.3390/agriculture13050965, 2023.
van Klompenburg, T., Kassahun, A., and Catal, C.: Crop yield prediction using machine learning: A systematic literature review, Comput. Electron. Agr., 177, 105709, https://doi.org/10.1016/j.compag.2020.105709, 2020.
Védère, C., Lebrun, M., Honvault, N., Aubertin, M.-L., Girardin, C., Garnier, P., Dignac, M.-F., Houben, D., and Rumpel, C.: How does soil water status influence the fate of soil organic matter? A review of processes across scales, Earth-Sci. Rev., 234, 104214, https://doi.org/10.1016/j.earscirev.2022.104214, 2022.
Wadoux, A. M. J. C., Roman Dobarco, M., Malone, B., Minasny, B., McBratney, A., and Searle, R.: Soil and Landscape Grid National Soil Attribute Maps – Organic Carbon (3′′ resolution) – Release 2. v3. [data set], https://doi.org/10.25919/ejhm-c070, 2022.
Webb, M. A., Kidd, D., and Minasny, B.: Near real-time mapping of air temperature at high spatiotemporal resolutions in Tasmania, Australia, Theor. Appl. Climatol., 141, 1181–1201, https://doi.org/10.1007/s00704-020-03259-4, 2020.
Wei, Z., Meng, Y., Zhang, W., Peng, J., and Meng, L.: Downscaling SMAP soil moisture estimation with gradient boosting decision tree regression over the Tibetan Plateau, Remote Sens. Environ., 225, 30–44, https://doi.org/10.1016/j.rse.2019.02.022, 2019.
Widyastuti, M.: marliana-widyastuti2/sm-map-tas: v1.0.0 (v1.0.0), Zenodo [code], https://doi.org/10.5281/zenodo.15134144, 2025 (data available at: https://github.com/marliana-widyastuti/sm-map-tas.git, last access: 4 April 2025)
Wimalathunge, N. S. and Bishop, T. F. A.: A space–time observation system for soil moisture in agricultural landscapes, Geoderma, 344, 1–13, https://doi.org/10.1016/j.geoderma.2019.03.002, 2019.
Xu, M., Yao, N., Yang, H., Xu, J., Hu, A., Gustavo Goncalves de Goncalves, L., and Liu, G.: Downscaling SMAP soil moisture using a wide and deep learning method over the Continental United States, J. Hydrol., 609, 127784, https://doi.org/10.1016/j.jhydrol.2022.127784, 2022.
Xu, W., Zhang, Z., Long, Z., and Qin, Q.: Downscaling SMAP Soil Moisture Products With Convolutional Neural Network, IEEE J. Sel. Top. Appl., 14, 4051–4062, https://doi.org/10.1109/JSTARS.2021.3069774, 2021.
Yang, M., Wang, G., Lazin, R., Shen, X., and Anagnostou, E.: Impact of planting time soil moisture on cereal crop yield in the Upper Blue Nile Basin: A novel insight towards agricultural water management, Agr. Water Manage., 243, 106430, https://doi.org/10.1016/j.agwat.2020.106430, 2021.
Yao, Y., Zhao, Y., Li, X., Feng, D., Shen, C., Liu, C., Kuang, X., and Zheng, C.: Can transfer learning improve hydrological predictions in the alpine regions?, J. Hydrol., 625, 130038, https://doi.org/10.1016/j.jhydrol.2023.130038, 2023.
Young, R., Walker, J., Yeoh, N., Smith, A., Ellett, K., Merlin, O., and Western, A.: Soil moisture and meteorological observations from the Murrumbidgee catchment, Department of Civil and Environmental Engineering, University of Melbourne, https://www.researchgate.net/publication/267832777 (last access: 23 August 2023), 2008.
Zhang, J., Zeng, Y., and Starly, B.: Recurrent neural networks with long term temporal dependencies in machine tool wear diagnosis and prognosis, SN Applied Sciences, 3, 442, https://doi.org/10.1007/s42452-021-04427-5, 2021.
Zhao, H., Li, J., Yuan, Q., Lin, L., Yue, L., and Xu, H.: Downscaling of soil moisture products using deep learning: Comparison and analysis on Tibetan Plateau, J. Hydrol., 607, 127570, https://doi.org/10.1016/j.jhydrol.2022.127570, 2022.
Short summary
This work aims to predict soil water content at a fine spatiotemporal resolution (80 m grids, daily) to support agricultural management in Tasmania. It proves that transfer learning can improve the accuracy of deep learning models to predict multilevel soil moisture. We address the challenge of mapping soil moisture at field-scale resolution and integrate the model into a near-real-time monitoring system.
This work aims to predict soil water content at a fine spatiotemporal resolution (80 m grids,...
