A longitudinal analysis of soil salinity changes using remotely sensed imageries

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: May 6, 2024

Abstract Soil salinization threatens agricultural productivity, leading to desertification and land degradation. Given the challenges of conducting labor-intensive expensive field studies laboratory analyses on a large scale, recent efforts have focused leveraging remote sensing techniques study soil salinity. This assesses importance salinity indices’ derived from remotely sensed imagery. Indices Landsat 8 (L8) Sentinel 2 (S2) imagery are used in Random Forest (RF), eXtreme Gradient Boosting (XGBoost), Decision Tree (DT), Support Vector Machine (SVR) associated with electrical (EC) conductivity 280 samples across 24,000 hectares Northeast Iran. The results indicated that DT is best-performing method (RMSE = 12.25, MAE 2.15, R 0.85 using L8 data RMSE 10.9, 2.12, 0.86 S2 data). Also, showed Multi-resolution Valley Bottom Flatness (MrVBF), moisture index, Topographic Wetness Index (TWI), Position Indicator (TPI) most important indices. Subsequently, time series analysis reduction sodium levels regions installed drainage networks, underscoring effectiveness system. These findings can assist decision-making about use conservation efforts, particularly high

Language: Английский

---

Effects of management of plastic and straw mulching management on crop yield and soil salinity in saline-alkaline soils of China: A meta-analysis

Agricultural Water Management, Journal Year: 2025, Volume and Issue: 308, P. 109309 - 109309

Published: Jan. 16, 2025

Language: Английский

---

Spatial variability of soil salinity in coastal saline-alkali farmlands: A novel approach integrating a stacked model with the reconstructed in-situ hyperspectral feature

Computers and Electronics in Agriculture, Journal Year: 2025, Volume and Issue: 235, P. 110376 - 110376

Published: April 19, 2025

Language: Английский

---

Exploring PlanetScope Satellite Capabilities for Soil Salinity Estimation and Mapping in Arid Regions Oases

Remote Sensing, Journal Year: 2023, Volume and Issue: 15(4), P. 1066 - 1066

Published: Feb. 15, 2023

One reason for soil degradation is salinization in inland dryland, which poses a substantial threat to arable land productivity. Remote-sensing technology provides rapid and accurate assessment salinity monitoring, but there lack of high-resolution remote-sensing spatial estimations. The PlanetScope satellite array high-precision mapping surface monitoring through its 3-m resolution near-daily revisiting frequency. This study’s use the new attempt estimate drylands. We hypothesized that field observations, data, spectral indices derived from data using partial least-squares regression (PLSR) method would produce reasonably regional maps based on 84 ground-truth various parameters, like band reflectance, published indices. results showed newly constructed red-edge yellow indices, we were able develop several inversion models maps. Different algorithms, including Boruta feature preference, Random Forest algorithm (RF), Extreme Gradient Boosting (XGBoost), applied variable selection. (YRNDSI YRNDVI) had best Pearson correlations 0.78 −0.78. also found proportions bands accounted large proportion essential strategies three with preference at 80%, RF XGBoost 60%, indicating these two contributed more estimation results. PLSR model different XGBoost-PLSR coefficient determination (R2), root mean square error (RMSE), ratio performance deviation (RPD) values 0.832, 12.050, 2.442, respectively. These suggest has potential significantly advance research by providing wealth fine-scale information.

Language: Английский

---

Impacts of climate change on the wetlands in the arid region of Northwestern China over the past 2 decades

Ecological Indicators, Journal Year: 2023, Volume and Issue: 149, P. 110168 - 110168

Published: March 27, 2023

Climate change has caused inland wetlands shrinkage and exacerbated problems, such as sustainable development ecological security, for years. These issues are mainly pronounced in the arid area. The environment's deterioration is especially severe drylands of interior. However, dryland wetland changes their response to climate poorly understood. This study uses K-means algorithm Google Earth Engine (GEE) classify two typical (Ebinur Bosten Lakes) rapidly accurately detecting changes. Moreover, it explores long-term spatial–temporal variation distribution. In addition, investigates various lakes northern southern Xinjiang using wavelet analysis. study's results showed that clustering GEE platform a high classification accuracy (Kappa > 0.8) classification, making feasible approach. terminal lake types, represented by Ebinur Lake, changed significantly between 2001 2021. contrast, inflow-outflow perform more consistently. Significant observed at with gradually shrinking transforming into marsh, where largest marsh proportion degrades non-wetland during year. Lake experienced frequent conversions throughout Furthermore, responses consistent, low precedes precipitation follows evapotranspiration. sensitivity varies, being most affected change. Mastering dynamic achieves goals drylands, including carbon neutrality peak dioxide emissions.

Language: Английский

---

Mapping soil organic matter and identifying potential controls in the farmland of Southern China: Integration of multi‐source data, machine learning and geostatistics

Land Degradation and Development, Journal Year: 2023, Volume and Issue: 34(17), P. 5468 - 5485

Published: Aug. 15, 2023

Abstract Soil organic matter (SOM) plays a critical role in terrestrial ecosystem functioning and is closely related to many global issues like soil fertility, health climate regulation. Therefore, obtaining accurate information on the spatial distribution of SOM its potential controlling factors interest. However, this remains great challenge since affected by numerous natural anthropogenic usually showed strong heterogeneity. In study, we collected total 16,580 surface (0–20 cm) samples from farmland throughout Jiangxi Province. And Random Forest (RF), Cubist gradient‐boosted models were compared used define factor which most associated with SOM. Then ordinary kriging (OK) machine learning‐ordinary co‐kriging (ML‐COK) map We found that average, 30.86 g kg −1 was present Anthropogenic activities strongly level, five top 10 important are related. The straw return amount proved have largest importance (31.46%) for modelling significant ( p < 0.001) positive relationship between content returned detected. Additionally, returning improved crop production. derived Quaternary Subred Sand has highest (37.82 ). Crop rotation also rice‐bean system (34.27 With best performance, RF algorithm R 2 = 0.49, RMSE 6.77 ) selected identify primary control integrated COK, termed as ML‐COK, ML‐COK outperformed OK method mapping Province 0.351 Lin's concordance correlation coefficient 0.549. Farmland distributed central part province had high content. contrast, north, south east parts relatively low Our study offers new insight properties, identifying driving variation SOM, provides valuable making more reasonable environmentally friendly management measures.

Language: Английский

---

High-Precision Mapping of Soil Organic Matter Based on UAV Imagery Using Machine Learning Algorithms

Drones, Journal Year: 2023, Volume and Issue: 7(5), P. 290 - 290

Published: April 26, 2023

Soil organic matter (SOM) is a critical indicator of soil nutrient levels, and the precise mapping its spatial distribution through remote sensing essential for regulation, fertilization, scientific management protection. This information can offer decision support to agricultural departments various producers. In this paper, two new indices, NLIrededge2 GDVIrededge2, were proposed based on sensitive spectral response characteristics SOM in Northeast China. Nine parameters suitable modeling determined using competitive adaptive reweighted sampling (CARS) method, combined with spectrum reflectance, mathematical transformations vegetation so on. Then, utilizing unmanned aerial vehicle (UAV)-based multispectral images centimeter-level resolution, random forest machine learning algorithm was used construct inversion model study area. The results showed that performed best estimating (R2 = 0.91, RMSE 0.95, MBE 0.49, RPIQ 3.25) when compared other algorithms such as vector regression (SVR), elastic net, Bayesian ridge, linear regression. findings indicated negative correlation between content altitude. concluded could meet needs farmers obtain basic provide reference UAVs monitor SOM.

Language: Английский

---

Mapping soil salinity using a combination of vegetation index time series and single-temporal remote sensing images in the Yellow River Delta, China

CATENA, Journal Year: 2023, Volume and Issue: 231, P. 107313 - 107313

Published: June 23, 2023

Language: Английский

---

Assessment of ecological quality in Northwest China (2000–2020) using the Google Earth Engine platform: Climate factors and land use/land cover contribute to ecological quality

Journal of Arid Land, Journal Year: 2022, Volume and Issue: 14(11), P. 1196 - 1211

Published: Nov. 1, 2022

Abstract The ecological quality of inland areas is an important aspect the United Nations Sustainable Development Goals (UN SDGs). environment Northwest China vulnerable to changes in climate and land use/land cover, this arid region over last two decades are not well understood. This makes it more difficult advance UN SDGs develop appropriate measures at regional level. In study, we used Moderate Resolution Imaging Spectroradiometer (MODIS) products generate remote sensing index (RSEI) on Google Earth Engine (GEE) platform examine relationship between Xinjiang during (from 2000 2020). We analyzed a 21-year time series trends spatial characteristics quality. further assessed importance different environmental factors affecting through random forest algorithm using data from statistical yearbooks use products. Our results show that RSEI constructed GEE can accurately reflect information because contribution first principal component was higher than 90.00%. has increased significantly decades, with northern part having better southern part. slightly improved accounted for 31.26% total area Xinjiang, whereas only 3.55% classified as worsen (3.16%) or (0.39%) vast majority deterioration mainly occurred barren Temperature, precipitation, closed shrublands, grasslands savannas were top five RSEI. Environmental allocated weights categories. general, recovery been controlled by cover policy-driven restoration therefore crucial. Rapid monitoring projected aid advancement comprehensive assessment SDGs.

Language: Английский

---

Spatio-Temporal Changes in Water Use Efficiency and Its Driving Factors in Central Asia (2001–2021)

Remote Sensing, Journal Year: 2023, Volume and Issue: 15(3), P. 767 - 767

Published: Jan. 29, 2023

Although understanding the carbon and water cycles of dryland ecosystems in terms use efficiency (WUE) is important, WUE its driving mechanisms are less understood Central Asia. This study calculated Asian for 2001–2021 based on Google Earth Engine (GEE) platform analyzed spatial temporal variability using information entropy. The importance atmospheric factors, hydrological biological factors Asia was also explored a geographic detector. results show following: (1) average from 2.584–3.607 gCkg−1H2O, with weak inter-annual significant intra-annual distribution changes; (2) strong drivers, land surface temperature (LST) being strongest driver WUE, explaining 54.8% variation; (3) interaction can enhance effect by more than 60% between most vegetation which (TEM) cover (FVC) greatest, 68.1% change WUE. Furthermore, very low explanatory power (e.g., pressure (VAP), aerosol optical depth over (AOD), groundwater (GWS)) has enhancement effect. Vegetation an important link it to understand guide ecological restoration projects.

Language: Английский

---