KAN You See It? KANs and Sentinel for Effective and Explainable Crop Field Segmentation
Preprint
Abstract
Segmentation of crop fields is essential for enhancing agricultural productivity, monitoring crop health, and promoting sustainable practices. Deep learning models adopted for this task must ensure accurate and reliable predictions to avoid economic losses and environmental impact. The newly proposed Kolmogorov-Arnold networks (KANs) offer promising advancements in the performance of neural networks. This paper analyzes the integration of KAN layers into the U-Net architecture (U-KAN) to segment crop fields using Sentinel-2 and Sentinel-1 satellite images and provides an analysis of the performance and explainability of these networks. Our findings indicate a 2\% improvement in IoU compared to the traditional full-convolutional U-Net model in fewer GFLOPs. Furthermore, gradient-based explanation techniques show that U-KAN predictions are highly plausible and that the network has a very high ability to focus on the boundaries of cultivated areas rather than on the areas themselves. The per-channel relevance analysis also reveals that some channels are irrelevant to this task.Keywords
All Related Versions
This publication has 31 references indexed in Scilit:
- Semantic segmentation of satellite images for crop type identification in smallholder farmsThe Journal of Supercomputing, 2023
- Explainable AI for earth observation: A review including societal and regulatory perspectivesInternational Journal of Applied Earth Observation and Geoinformation, 2022
- Learning main drivers of crop progress and failure in Europe with interpretable machine learningInternational Journal of Applied Earth Observation and Geoinformation, 2021
- Evaluating explainable artificial intelligence methods for multi-label deep learning classification tasks in remote sensingInternational Journal of Applied Earth Observation and Geoinformation, 2021
- Precision Farming Technologies to Increase Soil and Crop Productivity2021
- Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AIInformation Fusion, 2020
- Evaluating the capability of the Sentinel 2 data for soil organic carbon prediction in croplandsISPRS Journal of Photogrammetry and Remote Sensing, 2019
- Generalised Dice Overlap as a Deep Learning Loss Function for Highly Unbalanced Segmentations2017
- A review of advanced machine learning methods for the detection of biotic stress in precision crop protectionPrecision Agriculture, 2014
- Twenty five years of remote sensing in precision agriculture: Key advances and remaining knowledge gapsBiosystems Engineering, 2013