Mapping Soil Salinity in Vietnam's Red River Delta and Assessing Farmers' Adaptive Capacity
A study co-authored by Duc Dung Tran (HAPRI Senior Research Associate) and colleagues combines machine learning, remote sensing and interviews with local people to map soil salinity in Vietnam's Red River Delta and to assess farmers' adaptive capacity. It finds that the coastal and riverside regions were the most affected by soil salinity, and that human and financial resources were the two most important factors influencing the adaptive capacity of farmers.
Context
Soil salinity is a grave environmental threat to agricultural development and food security in large parts of the world, especially in the situation of global warming and sea level rise. The authors note that reliable information on the adaptive capacity of farms plays a key role in reducing the socioeconomic effects of soil salinization, and helps policymakers and farmers propose more appropriate measures to combat the phenomenon.
Methods
The authors designed a theoretical framework that pairs an Xgboost (XGB) machine learning model with a set of optimization algorithms (the Pelican Optimization Algorithm, Siberian Tiger Optimization, the Serval Optimization Algorithm, Particle Swarm Optimization and the Grasshopper Optimization Algorithm), and applied it to Sentinel 1 and 2A remote sensing data to evaluate the geographical distribution of soil salinity. The models were assessed with the mean absolute error (MAE), the root mean square error (RMSE) and the correlation coefficient (R²). The adaptive capacity of farmers was evaluated through interviews with 87 households.
Key findings
All of the optimization algorithms tested were successful in improving the accuracy of the XGB model.
The XGB-POA model performed best, with an R² value of 0.968, followed by XGB-STO (0.967), XGB-SOA (0.966), and XGB-PSO and XGB-GOA (both 0.964).
The soil salinity map produced by the models indicated that the coastal and riverside regions were the most affected by soil salinity.
Human and financial resources were the two most important factors influencing the adaptive capacity of farmers.
Keywords:
Soil Salinity
Red River Delta
Machine Learning
Remote Sensing
Adaptive Capacity
Vietnam
Link:
Citation:
Nguyen, H. D., Dang, D. K., Lai, T. A. T., Tran, D. D., Shahabi, H., & Bui, Q. (2025). Predicting Soil Salinity in the Red River Delta (Vietnam) Using Machine Learning and Assessing Farmers' Adaptive Capacity. Natural Hazards and Earth System Sciences, 25(9), 3505-3524.
