Comparative Study of Back-Propagation Artificial Neural Network Models for Predicting Salinity Parameters Based on Spectroscopy Under Different Surface Conditions of Soda Saline–Alkali Soils DOI Creative Commons
Yigang Jing,

Xuelin You,

Mingxuan Lu

et al.

Agronomy, Journal Year: 2024, Volume and Issue: 14(10), P. 2407 - 2407

Published: Oct. 17, 2024

Soil salinization typically exerts a highly negative influence on soil productivity, crop yields, and ecosystem balance. As typical region afflicted by salinization, the soda saline–alkali soils in Songnen Plain of China demonstrate clear cracking phenomena. Nevertheless, overall spectral response to cracked surface has scarcely been studied. This study intends impact salt parameters process enhance measurement method used for salt-affected soil. To accomplish this goal, controlled desiccation experiment was carried out saline samples. A gray-level co-occurrence matrix (GLCM) calculated contrast (CON) texture feature measure extent dried Additionally, spectroscopy measurements were conducted under different conditions. Principal component analysis (PCA) subsequently performed downscale data band integration. Subsequently, prediction accuracy back-propagation artificial neural network (BP-ANN) models developed from principal components reflectance compared parameters. The results reveal that content is dominant factor determining soils, samples had highest model rather than uncracked blocks 2 mm comparison Furthermore, BP-ANN combining CON further developed, which can significantly with R2 values 0.93, 0.91, 0.74 ratio deviation (RPD) 3.68, 3.26, 1.72 salinity, electrical conductivity (EC), pH, respectively. These findings provide valuable insights into mechanism thereby advancing field hyperspectral remote sensing monitoring salinization. also aids enhancing design helpful local remediation supporting data.

Language: Английский

Multi‐Scale Soil Salinization Dynamics From Global to Pore Scale: A Review DOI Creative Commons
Nima Shokri, Amirhossein Hassani, Muhammad Sahimi

et al.

Reviews of Geophysics, Journal Year: 2024, Volume and Issue: 62(4)

Published: Sept. 27, 2024

Abstract Soil salinization refers to the accumulation of water‐soluble salts in upper part soil profile. Excessive levels salinity affects crop production, health, and ecosystem functioning. This phenomenon threatens agriculture, food security, stability, fertility leading land degradation loss essential services that are fundamental sustaining life. In this review, we synthesize recent advances at various spatial temporal scales, ranging from global core, pore, molecular offering new insights presenting our perspective on potential future research directions address key challenges open questions related salinization. Globally, identify significant understanding salinity, which (a) considerable uncertainty estimating total area salt‐affected soils, (b) geographical bias ground‐based measurements (c) lack information data detailing secondary processes, both dry‐ wetlands, particularly concerning responses climate change. At core scale, impact salt precipitation with evolving porous structure evaporative fluxes media is not fully understood. knowledge crucial for accurately predicting water due evaporation. Additionally, effects transport properties media, such as mixed wettability conditions, saline evaporation resulting patterns remain unclear. Furthermore, effective continuum equations must be developed represent experimental pore‐scale numerical simulations.

Language: Английский

Citations

24
Remote Sensing Application in Ecological Restoration Monitoring: A Systematic Review DOI Creative Commons

Ruozeng Wang,

Yonghua Sun,

Jinkun Zong

et al.

Remote Sensing, Journal Year: 2024, Volume and Issue: 16(12), P. 2204 - 2204

Published: June 17, 2024

In the context of continuous degradation global environment, ecological restoration has become a primary task in environmental governance. this process, remote sensing technology, as an advanced monitoring and analysis tool, plays key role restoration. This article reviews application technology monitoring. Based on comprehensive literature field sensing, it systematically summarizes major in-orbit spaceborne airborne sensors their related products. further proposes series evaluation indicators for from four aspects: forests, soil, water, atmosphere, elaborates calculation methods these indicators. addition, paper also evaluating effectiveness restoration, including subjective evaluation, objective methods. Finally, we analyze challenges faced by effectiveness, such issues with precision extraction, limitations spatial resolution, diversity review looks forward to future technologies, potential applications integrated aerospace terrestrial multi-data fusion, machine learning technologies. study reveals monitoring, aiming provide efficient tools innovative strategies assessment

Language: Английский

Citations

10
Unveiling soil salinity patterns in soda saline-alkali regions using Sentinel-2 and SDGSAT-1 thermal infrared data DOI Creative Commons
Zeyu Gao,

Xiaojie Li,

Lijun Zuo

et al.

Remote Sensing of Environment, Journal Year: 2025, Volume and Issue: 322, P. 114708 - 114708

Published: March 14, 2025

Language: Английский

Citations

1
A three-dimensional sampling design based on the coefficient of variation method for soil environmental damage investigation DOI
Yulan Tang, Xiaohan Zhang

Environmental Monitoring and Assessment, Journal Year: 2024, Volume and Issue: 196(3)

Published: Feb. 29, 2024

Language: Английский

Citations

7
The inversion of arid-coastal cultivated soil salinity using explainable machine learning and Sentinel-2 DOI Creative Commons
Pingping Jia, Junhua Zhang,

Yanning Liang

et al.

Ecological Indicators, Journal Year: 2024, Volume and Issue: 166, P. 112364 - 112364

Published: July 29, 2024

Language: Английский

Citations

6
Spatiotemporal Variation and Future Predictions of Soil Salinization in the Werigan–Kuqa River Delta Oasis of China DOI Open Access
Baozhong He, Jianli Ding, Wenjiang Huang

et al.

Sustainability, Journal Year: 2023, Volume and Issue: 15(18), P. 13996 - 13996

Published: Sept. 21, 2023

Soil salinization is a serious global issue; by 2050, without intervention, 50% of the cultivated land area will be affected salinization. Therefore, estimating and predicting future soil salinity crucial for preventing investigating potential arable resources. In this study, several machine learning methods (random forest (RF), Light Gradient Boosting Machine (LightGBM), Decision Tree (GBDT), eXtreme (XGBoost)) were used to estimate in Werigan–Kuqa River Delta Oasis region China from 2001 2021. The cellular automata (CA)–Markov model was predict types 2020 2050. LightGBM method exhibited highest accuracy, overall prediction accuracy had following order: > RF GBRT XGBoost. Moderately saline, severely saline soils dominant east south research area, while non-saline mildly widely distributed inner oasis area. A marked decreasing trend salt content observed 2021, with rate 4.28 g/kg·10 a−1. primary change included conversion soil. generalized difference vegetation index (51%), Bio (30%), temperature drought (27%) greatest influence, followed variables associated attributes (soil organic carbon stock) terrain (topographic wetness index, slope, aspect, curvature, topographic relief index). Overall, CA–Markov simulation resulted suitable (kappa = 0.6736). Furthermore, areas increase other levels continue decrease From 2046 numerous converted These results can provide support control, agricultural production, investigations future. gradual decline past 20 years may have large-scale reclamation, which has turned alkali into also related effective measures taken local government control

Language: Английский

Citations

12
Digital mapping of soil salinity with time-windows features optimization and ensemble learning model DOI Creative Commons
Shuaishuai Shi, Nan Wang, Songchao Chen

et al.

Ecological Informatics, Journal Year: 2024, Volume and Issue: unknown, P. 102982 - 102982

Published: Dec. 1, 2024

Language: Английский

Citations

4
An enhanced soil salinity estimation method for arid regions using multisource remote sensing data and advanced feature selection DOI

Aihepa Aihaiti,

Ilyas Nurmemet, Xinru Yu

et al.

CATENA, Journal Year: 2025, Volume and Issue: 256, P. 109116 - 109116

Published: May 8, 2025

Language: Английский

Citations

0
Salinity Stress in Strawberry Seedlings Determined with a Spectral Fusion Model DOI Creative Commons
Haolin Yang, Xiaolei Zhang,

Yinyan Shi

et al.

Agronomy, Journal Year: 2025, Volume and Issue: 15(6), P. 1275 - 1275

Published: May 22, 2025

This article discusses the salt stress in strawberry seedlings under greenhouse conditions summer. Spectral acquisition equipment was used to obtain spectral data, and ambient leaf temperatures were combined model analyze relative chlorophyll content seedling leaves. Four different gradients employed culture seedings: S1 (0 mmol/L NaCl), S2 (50 S3 (100 S4 (150 NaCl). The results indicated that curves of groups began differentiate after day 3 (D3), their average canopy temperature increased by 2.5 °C 3.1 °C, respectively. performance traditional machine learning models integrating improved more than 80%. Under each treatment, one-dimensional ResNet integrated with performed best, root mean square absolute errors below 1.7 1.5, These highlight potential incorporating as an additional factor improve accuracy plant assessments. By enhances ability monitor health dynamically provides a comprehensive understanding how environmental factors influence physiology.

Language: Английский

Citations

0
Prediction of Soil Salinization in Arid Regions During Wet and Dry Seasons Based on Spectro‐Polarimetric Features and Machine Learning DOI

Xiaobing Wang,

Mireguli Ainiwaer,

Aizemaitijiang Maimaitituersun

et al.

Land Degradation and Development, Journal Year: 2025, Volume and Issue: unknown

Published: May 22, 2025

ABSTRACT Soil salinization is one of the main causes soil degradation and ecosystem deterioration in arid regions, posing a serious threat to ecological environments agricultural security. Understanding factors influencing crucial for management improvement. However, sensitivity seasonal changes has not been thoroughly studied regions. Therefore, this study focuses on Yanqi Basin, where 129 samples were collected (wet season 51, dry 78) laboratory analysis determine saturated extract conductivity (EC e ). salinity feature variables extracted from Sentinel‐1 radar remote sensing data, Sentinel‐2 optical digital elevation models (DEM). The Boruta algorithm was used select variables, optimal combined with Random Forest (RF), Support Vector Machine (SVM), Extreme Gradient Boosting (XGBoost) construct prediction models. results indicate: (1) Red‐edge spectral features (RE) can effectively predict salinization. In addition, most correlated EC are (DEM) river network baseline (CNBL), mainly because terrain area higher northwest lower southeast, flat farmland central region, movement water salt significantly influenced by terrain. (2) RF model best study, R 2 = 0.78, revealing spatial distribution during both wet seasons. (3) degree than due effects precipitation, vegetation cover, evaporation, migration. (4) During seasons, salinized concentrated along shores Bosten Lake, Kaidu River, Huangshui Ditch, while light distributed Gobi Desert areas. This provides scientific evidence improvement caused

Language: Английский

Citations

0