*Editorial* **Editorial for the Special Issue: "Integrated Applications of Geo-Information in Environmental Monitoring"**

**Weicheng Wu 1,2,\* and Yalan Liu <sup>3</sup>**


**Abstract:** Geo-information technology has been playing an increasingly important role in environmental monitoring in recent decades. With the continuous improvement in the spatial resolution of remote sensing images, the diversification of sensors and the development of processing packages, applications of a variety of geo-information, in particular, multi-resolution remote sensing and geographical data, have become momentous in environmental research, including land cover change detection and modeling, land degradation assessment, geohazard mapping and disaster damage assessment, mining and restoration monitoring, etc. In addition, machine learning algorithms such as Random Forests (RF) and Convolutional Neural Networks (CNN) have improved and deepened the applications of geo-information technology in environmental monitoring and assessment. The purpose of this Special Issue is to provide a platform for communication of high-quality research in the world in the domain of comprehensive application of geo-information technology. It contains 10 high-level scientific papers on the following topics such as desertification monitoring, governance of mining areas, identification of marine dynamic targets, extraction of buildings, and so on.

#### **1. Desertification and Sand-Control Monitoring and Assessment**

Soil degradation and even desertification are a serious environmental problem that affects the production activities and quality of life of local residents. Kim et al. developed a method fusing optical vegetation index and time-series phase coherence Synthetic Aperture Radar (SAR) data to monitor aeolian erosion sequences in desert areas using the Interferometric SAR (InSAR) technique. Additionally, the surface changes before and after desertification control activities in the Kubuqi Desert were monitored and analyzed [1], and the research demonstrates the effectiveness of InSAR techniques when applied for monitoring desertification and sand control. Li et al. [2] comprehensively evaluated sandcontrol effectiveness based on multitemporal Landsat images from 1990 to 2020 in the Mu Us Desert, China [2], by linking sand-control with socioeconomic and environmental data via multiple linear and logistic regression models. At the same time, the driving forces of desertification were also analyzed. This study shows that from 1991 to 2020, 8712 km<sup>2</sup> or 63% of the desert has been converted into pastures and shrublands with a greenness increase of 0.3509 in GDVI; the effectiveness of sand-control is favored by the rational agropastoral activities and policies; though desertification occurs locally, it is associated with both climatic and socioeconomic factors, such as wind speed, precipitation, water availability, distance to roads and animal husbandry. Globally, the rationalization of agricultural and animal husbandry activities through policies and other means is favorable for sand-control activities [2].

#### **2. Geohazard Mapping and Restoration Assessment in Mining Areas**

Since industrialization, mining activities have been increased significantly worldwide, causing a series of geo-environmental problems, especially geodisasters, for example, landslides, collapses and subsidence. Hence, high-resolution geohazard prediction

**Citation:** Wu, W.; Liu, Y. Editorial for the Special Issue: "Integrated Applications of Geo-Information in Environmental Monitoring". *Remote Sens.* **2022**, *14*, 4251. https:// doi.org/10.3390/rs14174251

Received: 11 June 2022 Accepted: 11 July 2022 Published: 29 August 2022

**Publisher's Note:** MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations.

**Copyright:** © 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https:// creativecommons.org/licenses/by/ 4.0/).

and mapping are essential but challenging due to limitations in the acquisition of highresolution data of the mining areas. In response to this problem, Qin et al. [3] combined geological prospecting data, topographic data and Gaofen-1 satellite data to construct a multi-source dataset and used machine learning technology to model the geological hazard in the Liaojiaping Orefield in Central China. The Random Forests (RF)-based mininginduced geohazard mapping (MGM) model they constructed shows excellent predictive performance, which provides a new method for geological hazard mapping [3]. Rare earth elements (REE) have a wide range of usages in the world, and the local enterprises and governments have heavily exploited these REE resources through open-pit or chemical leaching approaches in southern Jiangxi, China. Such REE mining has caused serious damage to the environment. Xie et al. [4] developed a new set of remote sensing indicators, i.e., Mining and Restoration Assessment Indicators (MRAIs), to assess land degradation caused by mining and the effectiveness of remediation. Compared with the single vegetation index, these new indicators have stronger sensitivity and wider dynamic range than the usual indices such as NDVI, GDVI, EVI, SAVI and ARVI. They are hence more suitable for evaluating the mining and recovery of REE mines [4]. This study not only provides more efficient remote sensing indicators for mining and restoration evaluation, but also makes up for the shortcomings of only relying on the known vegetation indices for evaluation of the restoration effectiveness.

#### **3. Improvement of Algorithms for Classification**

The rapid development of urbanization has led to a significant increase in the density of buildings. While providing convenience for living, problems such as illegal construction and conflicts between people and land are also prominent. It greatly increases the difficulty of supervision for governments. Therefore, remote sensing and geographic information technologies to accurately extract buildings and monitor them dynamically are one of the important applications of geo-information technology in environmental monitoring. Ma et al. [5] proposed an improved Convolutional Neural Network (CNN) Inception V3 architecture to evaluate the degree of damage to buildings after an earthquake in Yushu, Qinghai, China. This method improved the accuracy of classification and performed better than the traditional machine learning classifiers and also avoided the disadvantages of the traditional CNN, such as difficulty in function selection and image segmentation. Additionally, it provides a new attempt to evaluate the damage degree of buildings after the earthquake through remote sensing images. Wu et al. [6] proposed an improved anchor-free instance segmentation method based on CenterMask with spatial and channel attention-guided mechanisms for accurate extraction of buildings in high-resolution remote sensing images. In comparison with methods of Mask R-CNN, Mask Scoring R-CNN and CenterMask, their method is able to achieve the state-of-the-art performance at real-time speed, which makes it possible to extract buildings accurately in real time [6].

As a basic content of environmental monitoring, land use/land cover change (LUCC) monitoring has always been a research hotspot. Yu et al. [7] effectuated monitoring research on LUCC in the Xiong'an New Area based on new bands (purple, yellow, and red edges) of the GF-6 Wide Field of View (WFV) images (16 m in resolution) using the Double-Constrained Change Detection approach. The accuracy of monitoring through the two red-edge bands of GF-6WFV is higher than that of GF-1WFV. This result provides theoretical support for the application of GF-6WFV in LUCC study [7].

#### **4. Coastal and Ocean Applications**

Another major content included in this Special Issue is the application of optical and radar remote sensing to the coastal and oceanic research, for example, extraction and identification of coastlines and tracking the dynamic targets on the sea surface. The ocean occupies about 71% of the Earth's surface; it is rich in minerals and biological and chemical resources and has great development prospects. At the same time, socioeconomic development in the world has also brought about environmental problems in coastal areas and ocean such as sea level rise, marine debris and ocean garbage patches. However, limited by sensors and resolution, the monitoring of the marine environment has certain limitations. In recent years, with the rapid development of geo-information technology, many scholars have shifted the target of environmental monitoring from the traditional land surface to the ocean. Nazeer et al. [8] tracked the positional changes of the coastline by extracting historical coastline positions from topographic maps, medium-resolution Landsat (30 m) and high-resolution (3 m) imagery, respectively. Their research shows that human activities have a significant impact on the movement of the shoreline of Karachi. Additionally, the difference in human activities between the east and west coasts makes the coastline in the eastern region very fragile, while the western region is more stable. Therefore, management of the coast by the government and prevention of illegal marine encroachment are crucial for coastal protection [8]. Jiang et al. used the wideband echo simulation method based on a frequency domain to analyze the influence of ocean wave motion on the synthetic aperture radar (SAR) image of a target. Furthermore, they introduced a rectangular wavebeam-based geometrical optics and physical optics (GO/PO) method to calculate the electromagnetic (EM) scattering properties for the identification of complex targets [9]. The methods they proposed are capable of simulating the SAR image of the target on the sea surface, which is an important advancement in identifying dynamic targets on the sea surface. Massarelli et al. used high-resolution airborne data to identify and map mussel farming in the first and second inlet of Mar Piccolo, Italy. On this basis, factors that could harm the environmental status of the Mar Piccolo ecosystem were assessed. Their map made it possible to determine anthropogenic pressure on the Mar Piccolo of Taranto and the necessary actions for better management of the area [10].

**Author Contributions:** Conceptualization, W.W. and Y.L.; writing—original draft preparation, review, and editing, W.W. and Y.L. All authors have read and agreed to the published version of the manuscript.

**Funding:** This research received no external funding.

**Acknowledgments:** The Guest Editors of this Special Issue would like to thank all authors who have contributed to this volume for sharing their scientific results and for their excellent collaboration. Special gratitude will go to the community of distinguished reviewers for their constructive inputs. The *Remote Sensing* editorial team is acknowledged for its support during all phases related to the successful completion of this issue.

**Conflicts of Interest:** The author declares no conflict of interest.

#### **References**

