Uncertainty-Aware Interpretable Deep Learning for Slum Mapping and Monitoring

Abstract

Over a billion people live in slums, with poor sanitation, education, property rights and working conditions having a direct impact on current residents and future generations. Slum mapping is one of the key problems concerning slums. Policymakers need to delineate slum settlements to make informed decisions about infrastructure development and allocation of aid. A wide variety of machine learning and deep learning methods have been applied to multispectral satellite images to map slums with outstanding performance. Since the physical and visual manifestation of slums significantly varies with geographical region and comprehensive slum maps are rare, it is important to quantify the uncertainty of predictions for reliable and confident application of models to downstream tasks. In this study, we train a U-Net model with Monte Carlo Dropout (MCD) on 13-band Sentinel-2 images, allowing us to calculate pixelwise uncertainty in the predictions. The obtained outcomes show that the proposed model outperforms the previous state-of-the-art model, having both higher AUPRC and lower uncertainty when tested on unseen geographical regions of Mumbai using the regional testing framework introduced in this study. We also use SHapley Additive exPlanations (SHAP) values to investigate how the different features contribute to our model’s predictions which indicate a certain shortwave infrared image band is a powerful feature for determining the locations of slums within images. With our results, we demonstrate the usefulness of including an uncertainty quantification approach in detecting slum area changes over time.

Micro-Climate Computed Machine and Deep Learning Models for Prediction of Surface Water Temperature Using Satellite Data in Mundan Water Reservoir

“…The Mundan Reservoir showed some differences in the pixel-to-pixel comparison between Landsat-8 and Sentinel-3 products of the corresponding years, with the exception of S3 2016 and 2018-pixel, temperature readings being higher in the northern parts of the reservoir (red and orange color). The disparity can be attributed to uncertainties, biases, and errors in monitoring small inland waters using various sensors, which are caused by a variety of factors [67,68]. These factors include complex optical water properties, surface glint, atmospheric aerosol heterogeneity, and the proximity of reflecting surfaces.…”

Predicting housing deprivation from space in the slums of Dhaka

“…More recently, slum-mapping studies have focused on methodological advancements to develop models with increasing accuracy. For example, Stark et al (2019) and Wurm et al (2019) have explored the potential of fully convolutional neural networks, Stark et al (2020) developed a transfer-learned fully convolutional exception network while Fisher et al (2022) developed a convolutional deep learning model. However, these studies have focused on the morphological and geographic aspects of slum identification and delineation, but they have not considered living conditions of the people living in those slums.…”

Improvement of the Environment and Health in Terms of Governance of Slum Settlements through Collaboration Between Stakeholders

“…Slum residents experience a number of serious problems, including inadequate housing, poor sanitation, and limited access to essential services (Mukherjee et al, 2020a). Policymakers, academics, and international organizations have all taken an interest in the question of how to best manage slum areas (Fisher et al, 2022). Governments, non-governmental organizations, and members of the local community are just a few of the groups that have worked to better the lives of ghetto residents (Khan et al, 2022).…”