African soil properties and nutrients mapped at 30 m spatial resolution using two-scale ensemble machine learning

Scientific Reports, Journal Year: 2021, Volume and Issue: 11(1)

Published: March 17, 2021

Soil property and class maps for the continent of Africa were so far only available at very generalised scales, with many countries not mapped all. Thanks to an increasing quantity availability soil samples collected field point locations by various government and/or NGO funded projects, it is now possible produce detailed pan-African nutrients, including micro-nutrients fine spatial resolutions. In this paper we describe production a 30 m resolution Information System African using, date, most comprehensive compilation ([Formula: see text]) Earth Observation data. We produced predictions pH, organic carbon (C) total nitrogen (N), carbon, effective Cation Exchange Capacity (eCEC), extractable-phosphorus (P), potassium (K), calcium (Ca), magnesium (Mg), sulfur (S), sodium (Na), iron (Fe), zinc (Zn)-silt, clay sand, stone content, bulk density depth bedrock, three depths (0, 20 50 cm) using 2-scale 3D Ensemble Machine Learning framework implemented in mlr (Machine R) package. As covariate layers used 250 (MODIS, PROBA-V SM2RAIN products), (Sentinel-2, Landsat DTM derivatives) images. Our fivefold Cross-Validation results showed varying accuracy levels ranging from best performing pH (CCC = 0.900) more poorly predictable extractable phosphorus 0.654) sulphur 0.708) bedrock. Sentinel-2 bands SWIR (B11, B12), NIR (B09, B8A), bands, vertical derived DTM, overall important covariates. Climatic data images-SM2RAIN, bioclimatic variables MODIS Land Surface Temperature-however, remained as predicting chemical continental scale. This publicly 30-m aims supporting numerous applications, fertilizer policies investments, agronomic advice close yield gaps, environmental programs, or targeting nutrition interventions.

Language: Английский

---

Using soil library hyperspectral reflectance and machine learning to predict soil organic carbon: Assessing potential of airborne and spaceborne optical soil sensing

Remote Sensing of Environment, Journal Year: 2022, Volume and Issue: 271, P. 112914 - 112914

Published: Feb. 2, 2022

Language: Английский

---

Geomorphometry and terrain analysis: data, methods, platforms and applications

Earth-Science Reviews, Journal Year: 2022, Volume and Issue: 233, P. 104191 - 104191

Published: Sept. 19, 2022

Terrain is considered one of the most essential natural geographic features and a key factor in physical processes. Geomorphometry terrain analyses have provided wealth topographic data corresponding tools, thus delivering insights into geomorphology, hydrology, soil science, information systems (GIS) general. Recent advances analysis theory, methods, data-acquisition techniques platforms are impressive their ability to interpret not only multiscale multiaspect characteristics but also mechanisms processes associated with morphodynamics. In this context, we review progress fields geomorphometry analysis, as well probable future paths these two fields. collection construction processes, novel models acquisition can support expression complex terrain, scholars explored data-related challenges such accuracy security utilized data. been successful constructing efficient frameworks, transforming units methodologies, highlighting semantics object continuity Earth's surface Moreover, terrain-related research calculations aided by various tools that powerful processing capabilities. Furthermore, application scopes broadened, especially cross-analyses which be integrated other disciplines.

Language: Английский

---

Tracking the Impact of the Land Cover Change on the Spatial-Temporal Distribution of the Thermal Comfort: Insights from the Qinhuai River Basin, China

Sustainable Cities and Society, Journal Year: 2024, Volume and Issue: unknown, P. 105916 - 105916

Published: Oct. 1, 2024

Language: Английский

---

Open Soil Spectral Library (OSSL): Building reproducible soil calibration models through open development and community engagement

PLoS ONE, Journal Year: 2025, Volume and Issue: 20(1), P. e0296545 - e0296545

Published: Jan. 13, 2025

Soil spectroscopy is a widely used method for estimating soil properties that are important to environmental and agricultural monitoring. However, bottleneck its more widespread adoption the need establishing large reference datasets training machine learning (ML) models, which called spectral libraries (SSLs). Similarly, prediction capacity of new samples also subject number diversity types conditions represented in SSLs. To help bridge this gap enable hundreds stakeholders collect affordable data by leveraging centralized open resource, Spectroscopy Global Good initiative has created Open Spectral Library (OSSL). In paper, we describe procedures collecting harmonizing several SSLs incorporated into OSSL, followed exploratory analysis predictive modeling. The results 10-fold cross-validation with refitting show that, general, mid-infrared (MIR)-based models significantly accurate than visible near-infrared (VisNIR) or (NIR) models. From independent model evaluation, found Cubist comes out as best-performing ML algorithm calibration delivery reliable outputs (prediction uncertainty representation flag). Although many well predicted, total sulfur, extractable sodium, electrical conductivity performed poorly all regions, some other nutrients physical performing one two regions (VisNIR NIR). Hence, use based solely on variations limitations. This study presents discusses resources were developed from aspects opening data, current limitations, future development. With genuinely science project, hope OSSL becomes driver community accelerate pace scientific discovery innovation.

Language: Английский

---

Soil variability and quantification based on Sentinel-2 and Landsat-8 bare soil images: A comparison

Remote Sensing of Environment, Journal Year: 2020, Volume and Issue: 252, P. 112117 - 112117

Published: Oct. 5, 2020

Language: Английский

---

Terrain Analysis in Google Earth Engine: A Method Adapted for High-Performance Global-Scale Analysis

ISPRS International Journal of Geo-Information, Journal Year: 2020, Volume and Issue: 9(6), P. 400 - 400

Published: June 17, 2020

Terrain analysis is an important tool for modeling environmental systems. Aiming to use the cloud-based computing capabilities of Google Earth Engine (GEE), we customized algorithm calculating terrain attributes, such as slope, aspect, and curvatures, different resolution geographical extents. The calculation method based on geometry elevation values estimated within a 3 × spheroidal window, it does not rely projected data. Thus, partial derivatives are calculated considering great circle distances reference nodes topographic surface. was developed using JavaScript programming interface online code editor GEE can be loaded custom package. also provides additional feature making visualization maps with dynamic legend scale, which useful mapping extents: from local global. We compared consistency proposed available but limited GEE, resulted in correlation 0.89 0.96 aspect slope over near-global respectively. In addition this, horizontal, vertical curvature site (Mount Ararat) their equivalent attributes System Automated Geospatial Analysis (SAGA), achieved between 0.98. visual correspondence TAGEE SAGA confirms its potential analysis. scalable adapted needs, benefiting high-performance GEE.

Language: Английский

---

Temporal mosaicking approaches of Sentinel-2 images for extending topsoil organic carbon content mapping in croplands

International Journal of Applied Earth Observation and Geoinformation, Journal Year: 2020, Volume and Issue: 96, P. 102277 - 102277

Published: Dec. 16, 2020

The spatial assessment of soil organic carbon (SOC) is a major environmental challenge, notably for evaluating stocks. Recent works have shown the capability Sentinel-2 to predict SOC content over temperate agroecosystems characterized with annual crops. However, because spectral models are only applicable on bare soils, mapping often obtained limited areas. A possible improvement increasing number pixels which can be retrieved by inverting reflectance spectra, consists using optical images acquired at several dates. This study compares different approaches Sentinel–2 temporal mosaicking produce composite multi-date image predicting agricultural topsoils. first approach was based per-pixel selection and driven surface characteristics: or dry with/without removing vegetation. second creating per-date either performance from single-date, average indicators soil. To characterize surface, Sentinel-1 (S1)-derived moisture and/or indices such as normalized difference vegetation index (NDVI), Normalized Burn Ratio 2 (NBR2), (BSI) (S2WI) were used separately in combination. highlighted following results: i) none mosaic improved model prediction compared best single-date image; ii) approaches, mosaics S1-derived content, lesser extent, NBR2 index, outperformed BSI but they did not increase area predicted; iii) trade-off between predicted achieved (R2 ~ 0.5, RPD 1.4, RMSE 3.7 g.kg-1) enabled more than double (*2.44) area. suggests that (moisture, soil, roughness…), preferably combination, might maintain acceptable accuracies whilst extending larger areas images.

Language: Английский

---

Mapping soil organic carbon stocks and trends with satellite-driven high resolution maps over South Africa

The Science of The Total Environment, Journal Year: 2021, Volume and Issue: 771, P. 145384 - 145384

Published: Jan. 27, 2021

Estimation and monitoring of soil organic carbon (SOC) stocks is important for maintaining productivity meeting climate change mitigation targets. Current global SOC maps do not provide enough detail landscape-scale decision making, allow tracking sequestration or loss over time. Using an optical satellite-driven machine learning workflow, we mapped (topsoil; 0 to 30 cm) under natural vegetation (86% land area) South Africa at m spatial resolution between 1984 2019. We estimate a total topsoil stock 5.6 Pg C with median density 6 kg m−2 (IQR: interquartile range 2.9 m−2). Over 35 years, predicted underwent net increase 0.3% (relative long-term mean) the greatest increases (1.7%) decreases (−0.6%) occurring in Grassland Nama Karoo biomes, respectively. At landscape scale, changes up 25% were evident some locations, as evidenced from fence-line contrasts, likely due local management effects (e.g. woody encroachment associated increased overgrazing decreased SOC). Our mapping approach exhibited lower uncertainty (R2 = 0.64; RMSE 2.5 m−2) less bias compared previous low-resolution (250–1000 m) national efforts (average R2 0.24; 3.7 trend map remains estimate, pending repeated measures samples same location (time-series); priority changes. While high can inform decisions aimed (natural solutions), potential are limited by soils. It also that such planting trees balance trade-offs carbon, biodiversity overall ecosystem function.

Language: Английский

---

Monitoring changes in global soil organic carbon stocks from space

Remote Sensing of Environment, Journal Year: 2022, Volume and Issue: 281, P. 113260 - 113260

Published: Sept. 18, 2022

Language: Английский

---