AI-Powered Algerian Forest Mapping

Read full text Summarise with VIRAT
Authors: Maha Bazouzi, Mouncef Mohammed Kadri, Mohammed Anis Zemali, Meziane Iftene, Mohammed El Amin Larabi
Cited by: 0
References: 13

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

This paper presents an AI-powered approach for mapping Algerian forests using Sentinel-2 satellite imagery and advanced deep learning techniques. We leverage ESA WorldCover for large-scale weak supervision and mitigate label noise through a robust training strategy centered on Deep Abstaining Classifier (DAC) loss. Our core model is DeepLabV3+ with six Sentinel-2 spectral bands and vegetation indices (NDVI, EVI, and SAVI). Validation uses a high-quality manually annotated dataset derived from Google Earth Pro imagery. The DeepLabV3+ model with DAC training achieves strong segmentation performance (accuracy: 96.26%; Dice: 92.04%; IoU: 85.26%; recall: 94.91%), outperforming the baseline U-Net. The DAC remains stronger than both CE and SCE under matched settings, clean/noisy ratio sensitivity identifies a stable optimum around a clean weight of 0.85–0.90, and spatial five-fold cross-validation provides explicit cross-region variance estimates. Overall, the framework produces spatially coherent forest predictions with robust behavior under noisy supervision.

Fields of Study & Subjects

Remote-Sensing Image Classification Remote Sensing in Agriculture Advanced Neural Network Applications

Publication details

Journal / source
International Electronic Conference on Applied Sciences (ASEC)
Pages
87–87
Publication date
23 March 2026
Language
EN