HIGHLIGHTS
SUMMARY
Rana and Suryanarayana analyzed the contribution of various LULC types on LST by comparing four machine_learning models (K-Nearest Neighbor, Artificial_Neural_Network, Random Tree, and Support Vector Machine). While those machine_learning (ML) and artificial_intelligence (AI) models have improved the overall prediction accuracy of LST, the black-box nature of these techniques has inevitably lowered the interpretability. XAI is a methodology that provides interpretation so that humans can understand the results predicted by the machine_learning algorithm. By integrating the XGBoost and SHAP model, the authors developed the LST model for several buffer distances and predicted the . . .
If you want to have access to all the content you need to log in!
Thanks :)
If you don't have an account, you can create one here.