Tytuł pozycji:
d'Alembert Convolution for Enhanced Spatio-Temporal Analysis of Forest Ecosystems
This paper presents a novel approach to enhance the spatiotemporal analysis of forest ecosystems using the d'Alembert convolution method. As forests face increasing threats from climate change, deforestation, and other environmental stresses, there is a growing need for advanced methods that provide more accurate and dynamic information on forest health and management. The d'Alembert convolution, integrating elements from wave equation theory and convolutional neural networks, enables the comprehensive analysis of remote sensing images by capturing both spatial and temporal variations. This methodology not only improves feature extraction, but also helps address the challenges associated with traditional image processing techniques, which often overlook the temporal dynamics of forests. Our results from applying the d'Alembert convolution to two benchmark datasets---DeepGlobe Land Cover 2018 and LoveDA---demonstrate significant improvements in the analysis of forest ecosystems. Specifically, the d'Alembert Network achieved superior performance metrics compared to existing methods, including higher accuracy in classifying various forest types and more effective monitoring of changes over time. This study confirms the potential of the d'Alembert convolution in enhancing forest ecosystem analysis, contributing to smarter forestry practices and better environmental stewardship.
1. This research paper has received funding from Horizon Europe Framework Programme (HORIZON), call Teaming for Excellence (HORIZON-WIDERA-2022-ACCESS-01-two-stage) - Creation of the centre of excellence in smart forestry “Forest 4.0” No. 101059985. This research has been co-funded by the European Union under the project "FOREST 4.0 - Ekscelencijos centras tvariai miško bioekonomikai vystyti" (Nr. 10-042-P-0002)
2. Main Track: Regular Papers
3. Opracowanie rekordu ze środków MNiSW, umowa nr POPUL/SP/0154/2024/02 w ramach programu "Społeczna odpowiedzialność nauki II" - moduł: Popularyzacja nauki (2025).
