A deep neural network (DNN), evolved from a traditional artificial neural network, has been seamlessly adapted for the spatial data domain over the years. Deep learning (DL) has been widely applied for a number of applications and a variety of thematic domains. This article reports on a systematic review of methods adapted in major DNN applications with remote sensing data published between 2010 and 2020 aiming to understand the major application area, a framework for model development and the prospect of DL application in spatial data analysis. It has been found that image fusion, change detection, scene classification, image segmentation, and feature detection are the most commonly used application areas. Based on the publication in these thematic areas, a generic framework has been devised to guide a model development using DL based on the methods followed in the past. Finally, recent trends and prospects in terms of data, method, and application of deep learning with remote sensing data are discussed. The review finds that while DL-based approaches have the potential to unfold hidden information, they face challenges in selecting the most appropriate data, methods, and model parameterizations which may hinder the performance. The increasing trend of application of DL in the spatial domain is expected to leverage its strength at its optimum to the research frontiers.
A new generation of interpretable machine learning models is tested and presented to predict landslide occurrences.• The traditional definition of black box is left in favor of tools that can be queried to understand the artificially intelligent decision.• A web-GIS platform has also been developed to showcase the potential of explainable artificial intelligence for geoscientific applications.
The initial inception of the landslide susceptibility concept defined it as a static property of the landscape, explaining the proneness of certain locations to generate slope failures. Since the spread of data-driven probabilistic solutions though, the original susceptibility definition has been challenged to incorporate dynamic elements that would lead the occurrence probability to change both in space and in time. This is the starting point of this work, which combines the traditional strengths of the susceptibility framework together with the strengths typical of landslide early warning systems. Specifically, we model landslide occurrences in the norther sector of Vietnam, using a multi-temporal landslide inventory recently released by NASA. A set of static (terrain) and dynamic (cumulated rainfall) covariates are selected to explain the landslide presence/absence distribution via a Bayesian version of a binomial Generalized Additive Models (GAM). Thanks to the large spatiotemporal domain under consideration, we include a large suite of cross-validation routines, testing the landslide prediction through random sampling, as well as through stratified spatial and temporal sampling. We even extend the model test towards regions far away from the study site, to be used as external validation datasets. The overall performance appears to be quite high, with Area Under the Curve (AUC) values in the range of excellent model results, and very few localized exceptions. This model structure may serve as the basis for a new generation of early warning systems. However, the use of The Climate Hazards group Infrared Precipitation with Stations (CHIRPS) for the rainfall component limits the model ability in terms of future prediction. Therefore, we envision subsequent development to take this direction and move towards a unified dynamic landslide forecast. Ultimately, as a proof-of-concept, we have also implemented a potential early warning system in Google Earth Engine.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.