Multi-Sensor Data and Image Fusion for Environmental Parameter Prediction with Uncertainty-Aware Deep Learning
Accurate environmental parameter prediction is essential for air quality management, precision agriculture, water resource protection, and urban climate adaptation. Traditional approaches rely on single-modality sensor data and point estimation, neglecting the complementary information available from remote sensing imagery and failing to quantify prediction uncertainty. This paper proposes MSAF-UQ, a Multi-Sensor Adaptive Fusion framework with Uncertainty Quantification for environmental parameter prediction. Three key innovations are introduced: (1) a Multi-Sensor Adaptive Fusion mechanism (MSAF) that employs self-attention alignment, cross-attention interaction, and adaptive gating to dynamically fuse heterogeneous sensor tabular data with satellite or UAV imagery, overcoming fixed-weight concatenation bottlenecks; (2) an Environment-Aware Uncertainty Decomposition (EAUD) framework that unifies Monte Carlo Dropout, deep ensemble learning, and conformal prediction to decompose total predictive uncertainty into epistemic, aleatoric, and distributional components, with a theoretically derived joint coverage probability lower bound; and (3) a Sensor-Weighted Adaptive Loss (SWAL) function that dynamically adjusts gradient contributions based on sample-level uncertainty and sensor reliability, enhancing learning on high-uncertainty samples. Systematic experiments on four cross-domain environmental benchmarks (Air Quality, Soil Moisture, Water Quality, and Urban Microclimate) demonstrate that MSAF-UQ achieves 23.1% and 25.8% improvements in RMSE and MAE, respectively, attains a PICP of 96.2% with 23.5% MPIW reduction, and exhibits strong cross-domain transferability with statistical significance (Wilcoxon rank-sum test, p < 0.01).
References
- Nguyen T X B, Rosser K, Chahl J. A review of modern thermal imaging sensor technology and applications for autonomous aerial navigation[J]. Journal of Imaging, 2021, 7(10): 217.
- Longmore S N, Collins R P, Pfeifer S, et al. Adapting astronomical source detection software to help detect animals in thermal images obtained by unmanned aerial systems[J]. International Journal of Remote Sensing, 2017, 38(8-10): 2623-2638.
- Qin H, Lu J, Feng J, et al. Multi-Sensor Data Fusion and Deep Feature-Based Classification for Mapping China's Coastal and Wetland Areas[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2025.
- Shao Z, Wang H, Cai Y, et al. UA-Fusion: Uncertainty-aware multimodal data fusion framework for 3D object detection of autonomous vehicles[J]. IEEE Transactions on Instrumentation and Measurement, 2025.
- Roy S, Saha S. Uncertainty quantification in deep neural networks for multi-sensor Earth observation[M]//Deep Learning for Multi-Sensor Earth Observation. Elsevier, 2025: 231-247.
- Ren H, Zhang W, Shi S, et al. UniSense: Spatial-Uncertainty-Aware Collaborative Sensing for Autonomous Driving[C]//Proceedings of the 23rd Annual International Conference on Mobile Systems, Applications and Services. 2025: 459-472.
- Li Z, Singh B S B. Autonomous Driving in Adverse Weather: A Multi-Modal Fusion Framework with Uncertainty-Aware Learning for Robust Obstacle Detection[J]. International Journal of Advanced Computer Science & Applications, 2025, 16(8).
- Yang Q, Zhao Y, Cheng H. Uncertainty-Aware Evidential Fusion for Multi-Modal Object Detection in Autonomous Driving[J]. Drones, 2026, 10(2): 130.