Vital for Sustainable Agriculture: Pedological Knowledge and Mapping

European Journal of Soil Science, Год журнала: 2025, Номер 76(1)

Опубликована: Янв. 1, 2025

ABSTRACT Over the past 60 years, efforts to enhance agricultural productivity have mainly focussed on optimising strategies such as use of inorganic fertilisers, advancements in microbiology and improved water management practices. Here, we emphasise critical role pedology a foundation soil long‐term sustainability. We will demonstrate how overlooking intrinsic properties soils can result detrimental effects overall Communication between academia, extension experts, consultants farmers often results an overemphasis surface layer, for example, 20 40 cm, neglecting functions that occur at depth. Soil health regenerative agriculture must be coupled with understanding dynamic system. find pedological knowledge digital mapping technologies are underused achieving sustainable agriculture. By bridging gap emerging technologies, provide land users tools needed make informed decisions, ensuring their practices not only increase production but also preserve future generations.

Язык: Английский

---

Artificial intelligence in soil science

European Journal of Soil Science, Год журнала: 2025, Номер 76(2)

Опубликована: Март 1, 2025

ABSTRACT Few would disagree that artificial intelligence (AI) holds potential for advancing knowledge and innovation. Over the past decades, substantial research has been devoted to development application of AI in soil science. While most today's applications science are related machine learning (ML), also encompasses other fields such as digital image analysis, natural language processing (NLP), expert systems, representation. This review aims provide a comprehensive overview A definition equates with rationality is provided, followed by typical classification into three main domains sensing interacting, reasoning decision‐making, predicting. From this framework, taxonomy derived serves basis literature review. The major findings follows: i) diverse, decision support classification, prediction ML systems; ii) currently almost exclusively characterized ML; iii) predominantly found field mapping pedotransfer functions; iv) used purposes. few notable exceptions stand apart from mainstream applications, particularly realms NLP, cognitive models, interpretable ML. Based on these findings, I discuss attention points, using at expense explanation lack integration algorithmic solutions. envision future developments could include use text recognition legacy profile data, providing new source information. Another promising line texts build meta‐analyses summarize growing body literature. These foster contributions research.

Язык: Английский

---

Machine Learning and Artificial Intelligence Applications in Soil Science

European Journal of Soil Science, Год журнала: 2025, Номер 76(2)

Опубликована: Март 1, 2025

ABSTRACT The awarding of the Nobel Prize in Physics to pioneers neural networks highlights their substantial influence across diverse disciplines, including soil science. This article explores evolution and transformative impact machine learning artificial intelligence (AI) These technologies have revolutionised modelling complex processes, enhancing our ability predict map properties, simulate water movement assess global carbon dynamics. discusses future directions for AI science, such as developing new mathematical matrices integrating with science knowledge improve precision efficiency assessments. As evolves, its potential includes generating hypotheses, optimising carbon–mineral associations better sequestration phenotyping high‐throughput data analysis. Integrating physical models could lead more precise, data‐driven management practices that support net‐zero, nature‐positive stewardship improved security.

Язык: Английский

---

Conceptualizing core aspects of circular economy in soil: A critical review and analysis

Critical Reviews in Environmental Science and Technology, Год журнала: 2025, Номер unknown, С. 1 - 31

Опубликована: Янв. 26, 2025

Язык: Английский

---

Digital mapping of soil organic carbon in a plain area based on time-series features

Ecological Indicators, Год журнала: 2025, Номер 171, С. 113215 - 113215

Опубликована: Фев. 1, 2025

Язык: Английский

---

Addressing Data Handling Shortcomings in Machine Learning Studies on Biochar for Heavy Metal Remediation

Journal of Hazardous Materials, Год журнала: 2025, Номер 491, С. 137887 - 137887

Опубликована: Март 10, 2025

Язык: Английский

---

Advancing soil texture and organic carbon spatial variability assessment: Integrating proximal γ-ray spectroscopy and electromagnetic induction via data fusion for site-independent analysis

CATENA, Год журнала: 2025, Номер 254, С. 108980 - 108980

Опубликована: Март 28, 2025

Язык: Английский

---

Mapping near-real-time soil moisture dynamics over Tasmania with transfer learning

SOIL, Год журнала: 2025, Номер 11(1), С. 287 - 307

Опубликована: Апрель 8, 2025

Abstract. Soil moisture, an essential parameter for hydroclimatic studies, exhibits considerable spatial and temporal variability, which complicates its mapping at high spatiotemporal resolutions. Although current remote sensing products offer global estimates of soil moisture fine resolutions, they do so a coarse resolution. Deep learning (DL) techniques have recently been employed to produce high-resolution maps various properties; however, these methods require substantial training data. This study sought map daily across Tasmania, Australia, 80 m resolution using limited set We assessed three modeling strategies: DL models calibrated Australian dataset (51 411 observation points), the Tasmanian (9825 transfer technique that transferred information from Tasmania region-specific also evaluated two approaches, i.e., multilayer perceptron (MLP) long short-term memory (LSTM). The included Moisture Active Passive (SMAP) dataset, weather data, elevation map, land cover, multilevel property as inputs generate surface (0–30 cm) subsurface (30–60 layers. Results showed (1) performed worse than regardless type approaches; (2) models, solely local resulted in shortcomings predicting moisture; (3) exhibited remarkable performance improvements (error reductions up 45 % 50 increase correlation) resolved drawbacks previous models. LSTM with had highest overall average mean absolute error (MAE) 0.07 m3 m−3 correlation coefficient (r) 0.77 stations layer well MAE=0.07m3m-3 r=0.69 layer. fine-resolution captured detailed landscape variation according four distinct seasons Tasmania. were then applied integrated into near-real-time monitoring system assist agricultural decision-making.

Язык: Английский

---

Soil Organic Carbon Prediction and Mapping in Morocco Using PRISMA Hyperspectral Imagery and Meta-Learner Model

Remote Sensing, Год журнала: 2025, Номер 17(8), С. 1363 - 1363

Опубликована: Апрель 11, 2025

Accurate mapping of soil organic carbon (SOC) supports sustainable land management practices and accounting initiatives for mitigating climate change impacts. This study presents a novel meta-learner framework that combines multiple machine learning algorithms spectra processing to optimize SOC prediction using the PRISMA hyperspectral satellite imagery in Doukkala plain Morocco. The employs two-layer structure models. first layer consists Random Forest (RF), Support Vector Regression (SVR), Partial Least Squares (PLSR). These base models were configured data smoothing, transformation, spectral feature selection techniques, based on 70/30% split. second utilizes ridge regression model as integrate predictions from Results indicated RF SVR performance improved primarily with selection, while PLSR was most influenced by smoothing. approach outperformed individual models, achieving an average relative improvement 48.8% over single R2 0.65, RMSE 0.194%, RPIQ 2.247. contributes development methodologies predicting properties data.

Язык: Английский

---

Characterising and quantifying soil clay-sized minerals using mid-infrared spectroscopy

Soil and Tillage Research, Год журнала: 2025, Номер 252, С. 106590 - 106590

Опубликована: Апрель 17, 2025

Язык: Английский

---