Soil Science-Informed Machine Learning

Geoderma, Journal Year: 2024, Volume and Issue: 452, P. 117094 - 117094

Published: Nov. 14, 2024

Language: Английский

---

Fine-resolution mapping of cropland topsoil pH of Southern China and its environmental application

Geoderma, Journal Year: 2024, Volume and Issue: 442, P. 116798 - 116798

Published: Feb. 1, 2024

Soil pH is one of the critical indicators soil quality. A fine resolution map urgently required to address practical issues agricultural production, environmental protection, and ecosystem functioning, which often fall short meeting demands for local applications. To fill this gap, we used data from an extensive survey 13,424 surface samples (0–0.2 m) across cropland Jiangxi Province in Southern China. Using digital mapping techniques with 46 covariates, produced a 30 m topsoil We integrate different variable selection algorithms machine learning methods. Our results indicate Random Forest covariates selected by recursive feature had best performance r 0.583 RMSE 0.41. The prediction interval coverage probability our was 0.92, indicating low estimated uncertainty. Climate identified as most predicting contribution 37.42 %, followed properties (29.09 %), management (21.86 parent material (6.22 biota (5.39 %) factors. mean 5.21, great pressure acidification region. high values were mainly distributed Northern, Western, Eastern parts region while majorly located central part. Compared past surveys 1980 s, there no significant change surveyed can provide important implications guidance decisions on heavy metal pollution remediation, precision agriculture, prevention acidification.

Language: Английский

---

Vital for Sustainable Agriculture: Pedological Knowledge and Mapping

European Journal of Soil Science, Journal Year: 2025, Volume and Issue: 76(1)

Published: Jan. 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.

Language: Английский

---

Prediction accuracy of pXRF, MIR, and Vis‐NIR spectra for soil properties—A review

Soil Science Society of America Journal, Journal Year: 2025, Volume and Issue: 89(2)

Published: March 1, 2025

Abstract Here, we review the prediction accuracy for soil properties using portable X‐ray fluorescence (pXRF), mid‐infrared (MIR), and visible near‐infrared (Vis‐NIR) factors impacting predictions its accuracy. In total, 305 published papers were reviewed, most of them from Australia, Brazil, China, United States. About 44% focused on organic carbon (SOC) Vis‐NIR spectra. Partial least squares regression was frequently used. Most studies sampled Alfisols, Inceptisols, Entisols, up to 40‐cm depth. Researcher‐based (type or brand spectrometers, which differ in hardware, spectral range, resolution, calibration protocols; preprocessing methods; models; analysis methods calibration) soil‐based (horizon depth) explored. MIR spectra had better with a mean R 2 over 0.8 sand, clay, total N, C (TC), SOC inorganic (SIC), cation exchange capacity compared pXRF. past 20 years, tended increase silt, SIC, matter, EC when spectra, TC CaCO 3 pXRF Preprocessing methods, calibration, type models (i.e., machine deep learning), source (Vis‐NIR, MIR, pXRF), are used reduce noise multicollinearity, calibrate data, smooth all affected prediction. general, obtained highest properties. Future should focus effects (parent material, mineralogy, pedogenesis, type, horizon/depth) physical chemical

Language: Английский

---

Integrating Remote Sensing, GIS, and AI Technologies in Soil Erosion Studies

IntechOpen eBooks, Journal Year: 2025, Volume and Issue: unknown

Published: March 7, 2025

Soils are one of the most valuable non-renewable natural resources, and conserving them is critical for agricultural development ecological sustainability because they provide numerous ecosystem services. Soil erosion, a complex process caused by forces such as rainfall wind, poses significant challenges to ecosystems, agriculture, infrastructure, water quality, necessitating advanced monitoring modeling techniques. It has become global issue, threatening systems food security result climatic changes human activities. Traditional soil erosion field measurement methods have limitations in spatial temporal coverage. The integration new techniques remote sensing (RS), geographic information (GIS), artificial intelligence (AI) revolutionized our approach understanding managing erosion. RS technologies widely applicable investigations due their high efficiency, time savings, comprehensiveness. In recent years, advancements sensor technology resulted fine spatial-resolution images increased accuracy detection mapping purposes. Satellite imagery provides data on land cover properties, whereas digital elevation models (DEMs) detailed required assess slope flow accumulation, which important factors modeling. GIS enhances analysis integrating multiple datasets, making it easier identify hot spots utilizing like Revised Universal Loss Equation (RUSLE) estimate loss guide management decisions. Furthermore, AI techniques, particularly machine learning (ML) deep (DL), significantly improve predictions analyzing historical extracting relevant features from imagery. These use convolutional neural networks (CNNs) augmentation, well risk factors. Additionally, innovative methods, including biodegradable materials, hydroseeding, autonomous vehicles precision being developed prevent mitigate effectively. Although specific case studies demonstrate successful implementation this integrated framework variety landscapes, ongoing availability model validation must be addressed. Ultimately, collaboration RS, GIS, not only but also paves way effective control strategies, underscoring importance continued research vital area. This chapter addresses basic concerns related application erosion: concepts, acquisition, tools, types, management, visualization, an overview type its role

Language: Английский

---

Insights into micro-and nano-zero valent iron materials: synthesis methods and multifaceted applications

RSC Advances, Journal Year: 2024, Volume and Issue: 14(41), P. 30411 - 30439

Published: Jan. 1, 2024

The growing threat of environmental pollution to global health necessitates a focus on the search for sustainable wastewater remediation materials coupled with innovative strategies.

Language: Английский

---

A global soil spectral grid based on space sensing

The Science of The Total Environment, Journal Year: 2025, Volume and Issue: 968, P. 178791 - 178791

Published: Feb. 20, 2025

Language: Английский

---

Large-Scale Soil Organic Carbon Estimation via a Multisource Data Fusion Approach

Remote Sensing, Journal Year: 2025, Volume and Issue: 17(5), P. 771 - 771

Published: Feb. 23, 2025

This study presents a methodological framework for predicting soil organic carbon (SOC) using laboratory spectral recordings from handheld near-infrared (NIR, 1350–2550 nm) device combined with open geospatial data derived remote sensing sensors related to landform, climate, and vegetation. Initial experiments proved the superiority of convolutional neural networks (CNNs) only captured by low-cost devices reaching an R2 0.62, RMSE 0.31 log-SOC, RPIQ 1.87. Furthermore, incorporation geo-covariates Neo-Spectra substantially enhanced predictive capabilities, outperforming existing approaches. Although CNN-derived features had greatest contribution model, that were most informative model primarily rainfall data, valley bottom flatness, snow probability. The results demonstrate hybrid modeling approaches, particularly CNNs preprocess all fit prediction models Extreme Gradient Boosting trees, CNN-XGBoost, significantly outperformed traditional machine learning methods, notable reduction, 0.72, 2.17. findings this highlight effectiveness multimodal integration in enhancing accuracy SOC assessments. Finally, application interpretable techniques elucidated contributions various climatic topographical factors predictions, as well information, underscoring complex interactions affecting variability.

Language: Английский

---

Sensing and geotechnologies for soil characterization

Elsevier eBooks, Journal Year: 2025, Volume and Issue: unknown, P. 203 - 231

Published: Jan. 1, 2025

Language: Английский

---

Saturated Hydraulic Conductivity of Nine Soils According to Water Quality, Soil Texture, and Clay Mineralogy

Agronomy, Journal Year: 2025, Volume and Issue: 15(4), P. 864 - 864

Published: March 30, 2025

Water quality affects soils by promoting their degradation the accumulation of salts that will lead to salinization and sodification. However, magnitude these processes varies with soil attributes. Saturated hydraulic conductivity (Ksat) is rate at which water passes through saturated soil, fundamental determining movement profile. The Ksat may differ from according sodium adsorption ratio (SAR), electrical (ECw), texture, clay mineralogical assemblage. In this study, an experiment vertical columns constant-load permeameters was conducted evaluate changes in waters comprising five ECw values (128, 718, 1709, 2865, 4671 µS cm−1) SAR [0, 5, 12, 20, 30 (mmolc L−1)0.5] combination. Horizons nine northeastern Brazilian (ranging tropical semiarid) were selected texture composition. data obtained fit multiple regression equations for as a function SAR. This study also determined null each level, using = 0 on equation, predict needed achieve zero drainage level threshold electrolyte concentration (CTH) would 20% reduction maximum Ksat. Neither nor applied affected assemblage oxides kaolinite such Ferralsol, Nitisol, Lixisol, average 2.75, 6.06, 3.33 cm h−1, respectively. smectite- illite-rich soils, increased higher levels decreased levels, especially comparing soil’s estimated low high combination (ECw 128 cm−1 30) 0) Regosol (4.95 10.94 h−1); Vertisol (0.28 2.04 Planosol (0 0.29 Luvisol (0.46 2.12 Cambisol 0.23 Fluvisol (1.87 3.34 h−1). CTH easily reached concentrations highly active clays smectites. sandy target only under extremely values, indicating greater resistance salinization/sodification. Due assemblage, sub-humid/hot semiarid climates more treatments than humid/hot climates, serious risks physical chemical degradation. results showed importance monitoring irrigation, mainly less weathered, clayey activity minimize salt region. Our proved mineralogy had influence concentration, irrigated saline sodic waters, smectite are prone kaolinite.

Language: Английский

---