Advances in Sensor Data Fusion and AI for Environmental Monitoring

Dear Colleagues,

Environmental monitoring increasingly demands high-resolution, real-time, and reliable information to guide sustainability, disaster response, and ecosystem management. Advances in sensor technologies—including satellites, airborne platforms, in situ stations, and Internet of Things (IoT) devices—have enabled the collection of vast amounts of heterogeneous data (e.g., spectral, structural, chemical, and meteorological observations). However, transforming these multimodal streams into actionable insights remains challenging, necessitating effective data fusion strategies and robust artificial intelligence frameworks. This Topic emphasizes research at the intersection of sensor data fusion and AI-driven analytics, aiming to highlight innovations that integrate multi-source data for accurate environmental assessment and predictive modeling.

Contributions are encouraged in areas such as:

(1) Novel fusion algorithms for heterogeneous sensor integration, especially those improving spatial and temporal resolution;

(2) Deep learning models tailored to fused data for applications such as land-cover change, air and water quality, forest health, and disaster prediction;

(3) Scalable and efficient architectures—e.g., edge-to-cloud systems or federated learning—for near‑real‑time monitoring;

(4) Case studies demonstrating improved decision-making in forestry, agriculture, urban planning, or conservation. Ultimately, this Topic seeks to showcase multidisciplinary approaches that leverage sensor fusion and AI to advance environmental science and inform sustainable resource management.

Dr. Zhenyu Yu
Prof. Dr. Mohd Yamani Idna Idris
Prof. Dr. Yu Li
Dr. Aleksandar Dj Valjarević
Topic Editors