GA-Optimized Sampling for Soil Type Mapping in Plain Areas: Integrating Legacy Maps and Multisource Covariates DOI Creative Commons
Xiang‐Yuan Wu, Yan Li, Kening Wu

et al.

Agronomy, Journal Year: 2025, Volume and Issue: 15(4), P. 963 - 963

Published: April 15, 2025

Soil mapping plays a crucial role in optimizing agricultural production by providing spatially explicit information on soil types and properties, which supports decision-making precision fertilization, irrigation, crop selection. Traditional methods, rely field surveys laboratory analyses, face challenges related to efficiency scalability. Although combining legacy maps with environmental covariates can reveal soil–environment relationships improve sampling layouts, low spatial variability significant human activity plain areas often hinder the effectiveness of existing algorithms, making them sensitive sample density variability. This study proposes genetic algorithm (GA)-based optimization framework tailored By integrating covariates, GA dynamically balances dispersion representativeness, addressing limitations traditional methods homogeneous landscapes. In case conducted Tongzhou District, Beijing, China, method combined random forest modeling, applied type mapping, achieved highest kappa coefficient 70.25% 5000 points—an average improvement 10% over fuzzy C-means clustering K-nearest neighbor methods. Additionally, field-validated accuracy reached 89.69%, representing 13% other demonstrates that GA-based approach significantly enhances representativeness efficiency, thereby improving digital mapping. The proposed offers an efficient reliable solution for areas, contributing optimized land use more informed agriculture decisions.

Language: Английский

GA-Optimized Sampling for Soil Type Mapping in Plain Areas: Integrating Legacy Maps and Multisource Covariates DOI Creative Commons
Xiang‐Yuan Wu, Yan Li, Kening Wu

et al.

Agronomy, Journal Year: 2025, Volume and Issue: 15(4), P. 963 - 963

Published: April 15, 2025

Soil mapping plays a crucial role in optimizing agricultural production by providing spatially explicit information on soil types and properties, which supports decision-making precision fertilization, irrigation, crop selection. Traditional methods, rely field surveys laboratory analyses, face challenges related to efficiency scalability. Although combining legacy maps with environmental covariates can reveal soil–environment relationships improve sampling layouts, low spatial variability significant human activity plain areas often hinder the effectiveness of existing algorithms, making them sensitive sample density variability. This study proposes genetic algorithm (GA)-based optimization framework tailored By integrating covariates, GA dynamically balances dispersion representativeness, addressing limitations traditional methods homogeneous landscapes. In case conducted Tongzhou District, Beijing, China, method combined random forest modeling, applied type mapping, achieved highest kappa coefficient 70.25% 5000 points—an average improvement 10% over fuzzy C-means clustering K-nearest neighbor methods. Additionally, field-validated accuracy reached 89.69%, representing 13% other demonstrates that GA-based approach significantly enhances representativeness efficiency, thereby improving digital mapping. The proposed offers an efficient reliable solution for areas, contributing optimized land use more informed agriculture decisions.

Language: Английский

Citations

0