An interpretable deep learning framework for land use and land cover (LULC) classification in remote sensing using Shapley additive explanations (SHAPs) is introduced. It utilizes a compact convolutional neural network (CNN) model for the classification of satellite images and then feeds the results to a SHAP deep explainer so as to strengthen the classification results. The proposed framework is applied to Sentinel-2 satellite images containing 27000 images of pixel size $64 \times 64$ and operates on three-band combinations, reducing the model’s input data by 77% considering that 13 channels are available, while at the same time investigating on how different spectrum bands affect predictions on the dataset’s classes. Experimental results on the EuroSAT dataset demonstrate the CNN’s accurate classification with an overall accuracy of 94.72 %, whereas the classification accuracy on three-band combinations on each of the dataset’s classes highlights its improvement when compared to standard approaches with larger number of trainable parameters. The SHAP explainable results of the proposed framework shield the network’s predictions by showing correlation values that are relevant to the predicted class, thereby improving the classifications occurring in urban and rural areas with different land uses in the same scene.

The COVID-19 pandemic has affected many aspects of human life around the world, due to its tremendous outcomes on public health and socio-economic activities. Policy makers have tried to develop efficient responses based on technologies and advanced pandemic control methodologies, to limit the wide spreading of the virus in urban areas. However, techniques such as social isolation and lockdown are short-term solutions that minimize the spread of the pandemic in cities and do not invert long-term issues that derive from climate change, air pollution and urban planning challenges that enhance the spreading ability. Thus, it seems crucial to understand what kind of factors assist or prevent the wide spreading of the virus. Although AI frameworks have a very efficient predictive ability as data-driven procedures, they often struggle to identify strong correlations among multidimensional data and provide robust explanations. In this paper, we propose the fusion of a heterogeneous, spatio-temporal dataset that combine data from eight European cities spanning from 1 January 2020 to 31 December 2021 and describe atmospheric, socio-economic, health, mobility and environmental factors all related to potential links with COVID-19. Remote sensing data are the key solution to monitor the availability on public green spaces between cities in the study period. So, we evaluate the benefits of NIR and RED bands of satellite images to calculate the NDVI and locate the percentage in vegetation cover on each city for each week of our 2-year study. This novel dataset is evaluated by a tree-based machine learning algorithm that utilizes ensemble learning and is trained to make robust predictions on daily cases and deaths. Comparisons with other machine learning techniques justify its robustness on the regression metrics RMSE and MAE. Furthermore, the explainable frameworks SHAP and LIME are utilized to locate potential positive or negative influence of the factors on global and local level, with respect to our model’s predictive ability. A variation of SHAP, namely treeSHAP, is utilized for our tree-based algorithm to make fast and accurate explanations.

Detecting and localizing buildings is of primary importance in urban planning tasks. Automating the building extraction process, however, has become attractive given the dominance of Convolutional Neural Networks (CNNs) in image classification tasks. In this work, we explore the effectiveness of the CNN-based architecture U-Net and its variations, namely, the Residual U-Net, the Attention U-Net, and the Attention Residual U-Net, in automatic building extraction. We showcase their robustness in feature extraction and information processing using exclusively RGB images, as they are a low-cost alternative to multi-spectral and LiDAR ones, selected from the SpaceNet 1 dataset. The experimental results show that U-Net achieves a $91.9\%$ accuracy, whereas introducing residual blocks, attention gates, or a combination of both improves the accuracy of the vanilla U-Net to $93.6\%$, $94.0\%$, and $93.7\%$, respectively. Finally, the comparison between U-Net architectures and typical deep learning approaches from the literature highlights their increased performance in accurate building localization around corners and edges.

An efficient spectral band selection trustworthy Machine Learning (ML) framework for vineyard monitoring from UAV hyperspectral data is introduced. The UAV, equipped with Specim AFX-10, is used to capture data beyond the visible spectrum within the $400-1000$ nm wavelength range for a total of 224 bands. Popular supervised Machine Learning (ML) algorithms are utilized for detecting vegetation canopy in vineyards and distinguishing it from existing land uses, namely ground and shadow. Explainable AI (XAI) results accompany those from ML to identify the most important bands, and understand the contribution of their reflectance levels to the ML models. By doing so, the number of spectral bands is narrowed while maintaining the granularity of the HS data. Experimental results on UAVINE, a publicly available dataset within the context of this work, demonstrate excelling classification performance of Random Forest (RF) with an overall accuracy of 97.06%, and with precision, recall and F1-scores following accordingly. With the use of the computationally efficient Tree SHAP algorithm applied on the RF, the bands B106 (677nm- Red), B186 (897nm- NIR) and B211 (967nm- NIR) and B39 (498nm- Green) were identified as the most important ones to the model, enabling better visualization of the vineyard and band-based analysis for each one of the classes existing within the vineyard.