Machine Learning and Spatio Temporal Analysis for Assessing Ecological Impacts of the Billion Tree Afforestation Project

Ecology and Evolution, Journal Year: 2025, Volume and Issue: 15(2)

Published: Feb. 1, 2025

ABSTRACT This study evaluates the Billion Tree Afforestation Project (BTAP) in Pakistan's Khyber Pakhtunkhwa (KPK) province using remote sensing and machine learning. Applying Random Forest (RF) classification to Sentinel‐2 imagery, we observed an increase tree cover from 25.02% 2015 29.99% 2023 a decrease barren land 20.64% 16.81%, with accuracy above 85%. Hotspot spatial clustering analyses revealed significant vegetation recovery, high‐confidence hotspots rising 36.76% 42.56%. A predictive model for Normalized Difference Vegetation Index (NDVI), supported by SHAP analysis, identified soil moisture precipitation as primary drivers of growth, ANN achieving R 2 0.8556 RMSE 0.0607 on testing dataset. These results demonstrate effectiveness integrating learning framework support data‐driven afforestation efforts inform sustainable environmental management practices.

Language: Английский

---

Empirical estimation of saturated soil-paste electrical conductivity in the EU using pedotransfer functions and Quantile Regression Forests: A mapping approach based on LUCAS topsoil data

Geoderma, Journal Year: 2025, Volume and Issue: 454, P. 117199 - 117199

Published: Feb. 1, 2025

Language: Английский

---

Sentinel-2 and Sentinel-1 Bare Soil Temporal Mosaics of 6-year Periods for Soil Organic Carbon Content Mapping in Central France

Remote Sensing, Journal Year: 2023, Volume and Issue: 15(9), P. 2410 - 2410

Published: May 4, 2023

Satellite-based soil organic carbon content (SOC) mapping over wide regions is generally hampered by the low sampling density and diversity of periods. Some unfavorable topsoil conditions, such as high moisture, rugosity, presence crop residues, limited amplitude SOC values area bare when a single image used, are also among influencing factors. To generate reliable map, this study addresses use Sentinel-2 (S2) temporal mosaics (S2Bsoil) 6 years jointly with moisture products (SMPs) derived from Sentinel 1 2 images, measurement data other environmental covariates digital elevation models, lithology maps airborne gamma-ray data. In study, we explore (i) dates periods that preferable to construct soils while accounting for management; (ii) which set more relevant explain variability. From four sets covariates, best contributing was selected, median along uncertainty at 90% prediction intervals were mapped 25-m resolution quantile regression forest models. The accuracy predictions assessed 10-fold cross-validation, repeated five times. models using all had model performance. Airborne thorium, slope S2 bands (e.g., 6, 7, 8, 8a) indices calcareous sedimentary rocks, “calcl”) “late winter–spring” time series most important in model. Our results indicated role neighboring topographic distances oblique geographic coordinates between remote sensing parent material. These contributed not only optimizing performance but provided information related long-range gradients spatial variability, makes sense pedological point view.

Language: Английский

---

Satellite-based soil organic carbon mapping on European soils using available datasets and support sampling

Science of Remote Sensing, Journal Year: 2024, Volume and Issue: 9, P. 100118 - 100118

Published: Jan. 28, 2024

Soil organic carbon (SOC) plays a major role in the global cycle and is an important factor for soil health fertility. Accurate mapping of SOC other influencing parameters are crucial to guide optimization agricultural land management maintain restore health, increase fertility, thus quantify its potential sequestering CO2. Remote sensing machine learning techniques offer promising approaches predicting distribution. In this study, we used remote data algorithms map at regional large scale, which then combined with temporospatial spectral signature-based sampling integrate local ground measurements. A rigorous validation approach was performed where several independent unseen datasets high number samples were used, additionally involved densely sampled fields. We found that our could predict average percentage error less than 10 % R2 0.91 using support on croplands located mineral soils, demonstrating sensing, learning, specific measurements SOC. Our results suggest make small differences measurable inform sequestration efforts improve understanding impacts use field practices cycling.

Language: Английский

---

Using local ensemble models and Landsat bare soil composites for large-scale soil organic carbon maps in cropland

Geoderma, Journal Year: 2024, Volume and Issue: 444, P. 116850 - 116850

Published: March 19, 2024

National soil organic carbon (SOC) maps are essential to improve greenhouse gas accounting and support climate-smart agriculture. Large-scale SOC models based on wall-to-wall information from remote sensing remain a challenge due the high diversity of natural conditions difficulty for spatial location samples. In this study, we tested if implementation local ensemble (LEM) can be used predictions Landsat-based reflectance composites (SRC) Germany. For this, divided research area into 30 times km tiles calculated generalized linear (GLM) random, nearby observations. Based GLMs, were predicted aggregated using moving window approach. The variable importance was analyzed identify dependencies in correlation between SRC SOC. final map, Random Forest (RF) model trained predictions, SRC, full set training samples agricultural inventory. results show that LEM able accuracy (R2 = 0.68; RMSE 5.6 g kg−1), compared single, global 0.52; 6.8 kg−1). spectral bands showed clear patterns throughout area. Differences explained by conditions, influencing properties. Compared widely adopted integration distance covariates such as geographical coordinates, reduce autocorrelation greater extent prediction accuracy, especially underrepresented values. presents new method integrate increase interpretability DSM models.

Language: Английский

---

Influence of Soil Texture on the Estimation of Soil Organic Carbon From Sentinel‐2 Temporal Mosaics at 34 European Sites

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

Published: Jan. 1, 2025

ABSTRACT Multispectral imaging satellites such as Sentinel‐2 are considered a possible tool to assist in the mapping of soil organic carbon (SOC) using images bare soil. However, reported results variable. The measured reflectance surface is not only related SOC but also several other environmental and edaphic factors. Soil texture one factor that strongly affects reflectance. Depending on spatial correlation with SOC, influence may improve or hinder estimation from spectral data. This study aimed investigate these influences local models at 34 sites different pedo‐climatic zones across 10 European countries. were individual agricultural fields few close proximity. For each site, predict clay particle size fraction developed temporal mosaics images. Overall, predicting was difficult, prediction performances ratio performance deviation (RPD) > 1.5 observed 8 12 for clay, respectively. A general relationship between evident explained small part large variability we sites. Adding information additional predictors improved average, benefit varied average relative importance bands indicated red far‐red regions visible spectrum more important than prediction. opposite true region around 2200 nm, which models.

Language: Английский

---

High-Accuracy Mapping of Soil Organic Carbon by Mining Sentinel-1/2 Radar and Optical Time-Series Data with Super Ensemble Model

Remote Sensing, Journal Year: 2025, Volume and Issue: 17(4), P. 678 - 678

Published: Feb. 17, 2025

Accurate digital soil organic carbon mapping is of great significance for regulating the global cycle and addressing climate change. With advent remote sensing big data era, multi-source multi-temporal techniques have been extensively applied in Earth observation. However, how to fully mine time-series high-accuracy SOC remains a key challenge. To address this challenge, study introduced new idea mining data. We used 413 topsoil samples from southern Xinjiang, China, as an example. By (Sentinel-1/2) 2017 2023, we revealed temporal variation pattern correlation between Sentinel-1/2 SOC, thereby identifying optimal time window monitoring using integrating environmental covariates super ensemble model, achieved Southern China. The results showed following aspects: (1) windows were July–September July–August, respectively; (2) modeling accuracy sensor integrated with was superior single-source alone. In model based on data, cumulative contribution rate Sentinel-2 51.71% higher than that Sentinel-1 data; (3) stacking model’s predictive performance outperformed weight average simple models. Therefore, covariates, driven represents strategy mapping.

Language: Английский

---

Soil Organic Carbon Assessment for Carbon Farming: A Review

Agriculture, Journal Year: 2025, Volume and Issue: 15(5), P. 567 - 567

Published: March 6, 2025

This review is motivated by the urgent need to improve soil organic carbon (SOC) assessment methods, which are vital for enhancing health, addressing climate change, and promoting farming. By employing a structured approach that involves systematic literature search, data extraction, analysis, 86 relevant studies were identified. These evaluated address following specific research questions: (a) What state-of-the-art approaches in sampling, modeling, acquisition? (b) key challenges, open issues, potential advancements, future directions needed enhance effectiveness of farming practices? The findings indicate while traditional SOC techniques remain foundational, there significant shift towards incorporating model-based machine learning models, proximal spectroscopy, remote sensing technologies. emerging primarily serve as complementary laboratory analyses, overall accuracy reliability assessments. Despite these challenges such spatial temporal variability, high financial costs, limitations measurement continue hinder progress. also highlights necessity scalable, cost-effective, precise tools, alongside supportive policies incentives encourage farmer adoption. Finally, development “System-of-Systems” integrates sensing, modeling offers promising pathway balancing cost accuracy, ultimately supporting practices.

Language: Английский

---

Spectra-based predictive mapping of soil organic carbon in croplands: Single-date versus multitemporal bare soil compositing approaches

Geoderma, Journal Year: 2024, Volume and Issue: 449, P. 116987 - 116987

Published: Aug. 1, 2024

Sustainable cropland management requires quantitative and up-to-date information on the spatial pattern of soil organic carbon (SOC) at scales relevant for implementing targeted conservation measures. Spectra-based remote sensing SOC in croplands is promising, but it extraction high-quality bare pixels that enable spatially continuous coverage. Here, we aim to compare predictive capability single-date versus multitemporal compositing images an intensively cultivated region (4,700 km2) northeast China. A series 12 within 2017–2022 were processed passed onto three approaches (geometric median, univariate mean median) create mosaics. Both spectral images, together with laboratory-simulated Sentinel-2 benchmark data, used develop partial least squares regression, Cubist random forest models via 100 bootstrapped validations. With consistently being best performing algorithm all data sources, results show exhibited temporally unstable performance (R2: 0.30–0.67). Among approaches, high-dimensional geometric median composite was most suitable because (i) its close resemblance laboratory reference robustness outliers, which yielded a model 0.64; RMSE: 2.24 g/kg) outperforming 11 out models; (ii) ability retain between-band relationships allowed further incorporation SOC-relevant indexes, led 6.5 % increase prediction accuracy. The resultant map highlighted imaging reveal field-scale degradation patterns. Future work should explore possibility extending purely spectra-based framework integrated mapping monitoring additional biophysical information.

Language: Английский

---

A Deep Learning Approach to Estimate Soil Organic Carbon from Remote Sensing

Remote Sensing, Journal Year: 2024, Volume and Issue: 16(4), P. 655 - 655

Published: Feb. 10, 2024

Monitoring soil organic carbon (SOC) typically assumes conducting a labor-intensive sampling campaign, followed by laboratory testing, which is both expensive and impractical for generating useful, spatially continuous data products. The present study leverages the power of machine learning (ML) and, in particular, deep neural networks (DNNs) segmentation, as well satellite imagery, to estimate SOC remotely. We propose new two-stage pipeline remote estimation, relies on using DNN trained classify land cover perform feature extraction, while estimation performed different ML model. first stage an image segmentation with U-Net architecture, observed geographical region, based multi-spectral images taken Sentinel-2 constellation. This estimator subsequently used extract latent vector each output pixels, rolling back from (dense) layer accessing last available convolutional same dimension our desired output. second set vectors extracted at coordinates manual measurements exist. tested variety models report their performance. Using best extremely randomized trees model, we generated map estimations region Tuscany, Italy, resolution 10 m, share researchers means validating results demonstrate efficiency proposed approach, can easily be scaled create global map.

Language: Английский

---