Spatial heterogeneity response of soil salinization inversion cotton field expansion based on deep learning DOI Creative Commons
Jinming Zhang, Jianli Ding,

Jinjie Wang

et al.

Frontiers in Plant Science, Journal Year: 2024, Volume and Issue: 15

Published: Nov. 12, 2024

Soil salinization represents a significant challenge to the ecological environment in arid areas, and digital mapping of soil as well exploration its spatial heterogeneity with crop growth have important implications for national food security management. However, machine learning models currently used are deficient mining local information on salinity do not explore impacts crops. This study developed inversion using CNN (Convolutional Neural Network), LSTM (Long Short-Term Memory RF (Random Forest) based 97 field samples feature variables extracted from Landsat-8 imagery. By evaluating accuracy, best-performing model was selected map at 30m resolution years 2013 2022, relationship between electrical conductivity (EC) values expansion cotton fields their correlation. The results indicate that:(1) performs best prediction, an R

Language: Английский

Optimized irrigation level and deep vertical rotary tillage depth enhanced seed cotton yield, water-nitrogen productivity and economic benefit by reducing soil salinity: evidence from southern Xinjiang of China DOI
Zhentao Bai, Ling Li, Zhijie Li

et al.

Irrigation Science, Journal Year: 2025, Volume and Issue: unknown

Published: March 7, 2025

Language: Английский

Citations

1
Integrated deep vertical rotary tillage and subsurface pipe drainage techniques for sustainable soil salinization management and cotton production in arid regions DOI Creative Commons
Zhijie Li, Qiang Meng, Ling Li

et al.

Agricultural Water Management, Journal Year: 2025, Volume and Issue: 312, P. 109429 - 109429

Published: March 15, 2025

Language: Английский

Citations

1
Climate change promotes shifts of summer maize yield and water productivity in the Weihe River Basin: A regionalization study based on a distributed crop model DOI Creative Commons
Wenxin Xie,

Hui Ran,

Anni Deng

et al.

Agricultural Water Management, Journal Year: 2025, Volume and Issue: 314, P. 109500 - 109500

Published: May 1, 2025

Language: Английский

Citations

0
Monitoring soil salinization in Arid cotton fields using Unmanned Aerial Vehicle hyperspectral imagery DOI
Jinming Zhang, Jianli Ding, Jiao Tan

et al.

International Journal of Applied Earth Observation and Geoinformation, Journal Year: 2025, Volume and Issue: 140, P. 104584 - 104584

Published: May 9, 2025

Language: Английский

Citations

0
Spatial heterogeneity response of soil salinization inversion cotton field expansion based on deep learning DOI Creative Commons
Jinming Zhang, Jianli Ding,

Jinjie Wang

et al.

Frontiers in Plant Science, Journal Year: 2024, Volume and Issue: 15

Published: Nov. 12, 2024

Soil salinization represents a significant challenge to the ecological environment in arid areas, and digital mapping of soil as well exploration its spatial heterogeneity with crop growth have important implications for national food security management. However, machine learning models currently used are deficient mining local information on salinity do not explore impacts crops. This study developed inversion using CNN (Convolutional Neural Network), LSTM (Long Short-Term Memory RF (Random Forest) based 97 field samples feature variables extracted from Landsat-8 imagery. By evaluating accuracy, best-performing model was selected map at 30m resolution years 2013 2022, relationship between electrical conductivity (EC) values expansion cotton fields their correlation. The results indicate that:(1) performs best prediction, an R

Language: Английский

Citations

1