Methods in the spatial deep learning: current status and future direction

Abstract

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.

Forest fire pattern and vulnerability mapping using deep learning in Nepal

“…Fire-vulnerability modeling was performed using two approaches: MaxEnt, one of the most commonly used fire distribution modeling tools, and DNN, an emerging machine-learning approach that is reported to outperform many traditional machine-learning approaches in many thematic applications (Mishra et al 2022). The following subsections describe the selection of input variables, data division for training and testing, and model fitting processes.…”

“…On the other hand, deep-learning-based approaches such as deep neural network (DNN) and convolution neural networks (CNN), among others, are outperforming many other machine-learning methods for diverse applications in recent years (Mishra et al 2022;Zhang et al 2021). However, their applicability has not been fully explored in the case of forest fire modeling.…”

U-net-based semantic classification for flood extent extraction using SAR imagery and GEE platform: A case study for 2019 central US flooding

“…However, many traditional data collection systems face challenges such as the high cost and labor required to maintain existing stations and keep up with the rapid needs for creating new data that matches the pace of other changes such as land use change (Muste et al, 2017;Pike et al, 2019;WMO, 2015). Among all prospective developments that may increase data availability in the future, two components stand out, notably, crowd-sourced data and remotely sensed imagery (Mignot & Dewals, 2022;Mishra et al, 2022). Although both can cover a large area rapidly, remotely sensed imagery has a significant advantage in terms of data accuracy and temporal and spatial consistency.…”

“…Significant progress has been made in most of the aforementioned categories throughout the years ( Li et al, 2018;Lu et al, 2014;Tiwari et al, 2020;Ye et al, 2021) as a result of improved data storing and processing techniques and data availability. Water extent extraction using machine learning (ML) and deep learning (DL) algorithms has experienced explosive growth in recent years (Yu Bai et al, 2022;Mishra et al, 2022;Sit, Demiray, et al, 2021;Xiang et al, 2021) in various application scenarios such as delineating wetland areas (Salehi et al, 2018), monitoring spatial-temporal changes (Kseňak et al, 2022), long-term change detection (Zhang et al, 2020), agricultural field mapping (T. .…”

Application of improved deep forest algorithm in image recognition

“…Since the 1970s, it has been known as one of the three cuttingedge technologies in the world (space technology, energy technology and artificial intelligence), and it is also considered as the three cutting-edge technologies in the 21st century (genetic engineering, nanoscience and artificial intelligence) [1]. In recent 30 years, artificial intelligence has been widely used in many disciplines and achieved fruitful results, so it has developed rapidly and gradually become an independent branch, as well as a sound system both in theory and practice [2].…”