Yihan Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yihan Wang has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Yonghua Sun
Beijing Laboratory of Water Resources Security, Capital Normal University, Beijing 100048, China
3 shared publications - Ruozeng Wang
Beijing Laboratory of Water Resources Security, Capital Normal University, Beijing 100048, China
2 shared publications - Wangkuan Zhang
Beijing Laboratory of Water Resources Security, Capital Normal University, Beijing 100048, China
2 shared publications - Xinglu Cheng
Beijing Laboratory of Water Resources Security, Capital Normal University, Beijing 100048, China
2 shared publications - Xuyue Cao
Beijing Laboratory of Water Resources Security, Capital Normal University, Beijing 100048, China
2 shared publications - Yanzhao Wang
Beijing Laboratory of Water Resources Security, Capital Normal University, Beijing 100048, China
2 shared publications
Latest Publications
- Open Access
- 8 September 2026
- Published by MDPI AG in Remote Sensing
- Vol. 18 (18) , 3076
Multi-Temporal Phenology–Spectral Feature Optimization and Decision Tree Classification for Estuarine Wetland Vegetation Mapping
Estuarine wetlands are highly dynamic ecosystems, and the vegetation serves as a critical indicator of ecological health. Accurate mapping of different vegetation types remains challenging due to spectral similarities and the high dimensionality of time-series data. This research introduces a Google Earth Engine (GEE)-based hierarchical framework for mapping eight typical vegetation types in the Liaohe Estuary using Sentinel-2 imagery from 2023 to 2025. To address data redundancy, a novel feature selection algorithm based on Mahalanobis distance and class separability (FSMD-CS) was developed, reducing 225 dimensions to seven optimal variables. Integrated with a hierarchical decision tree calibrated using the SEaTH approach, the framework achieved an overall accuracy of 86.39% (kappa = 0.832), surpassing single-temporal spectral imagery classification and unoptimized MPS feature classification, which achieved OAs of 72.31% and 82.68%, respectively. The majority of selected features originate from the early green-up and late senescence stages, indicating that seasonal phenological metrics offer superior discrimination of vegetation types compared to peak-summer spectral data. Overall, the proposed framework provides an efficient and interpretable solution for fine-scale estuarine vegetation mapping.
- 8 September 2026
- Published by MDPI AG in Remote Sensing
- Vol. 18 (18) , 3076
Open AccessMulti-Temporal Phenology–Spectral Feature Optimization and Decision Tree Classification for Estuarine Wetland Vegetation Mapping
Estuarine wetlands are highly dynamic ecosystems, and the vegetation serves as a critical indicator of ecological health. Accurate mapping of different vegetation types remains challenging due to spectral similarities and the high dimensionality of time-series data. This research introduces a Google Earth Engine (GEE)-based hierarchical framework for mapping eight typical vegetation types in the Liaohe Estuary using Sentinel-2 imagery from 2023 to 2025. To address data redundancy, a novel feature selection algorithm based on Mahalanobis distance and class separability (FSMD-CS) was developed, reducing 225 dimensions to seven optimal variables. Integrated with a hierarchical decision tree calibrated using the SEaTH approach, the framework achieved an overall accuracy of 86.39% (kappa = 0.832), surpassing single-temporal spectral imagery classification and unoptimized MPS feature classification, which achieved OAs of 72.31% and 82.68%, respectively. The majority of selected features originate from the early green-up and late senescence stages, indicating that seasonal phenological metrics offer superior discrimination of vegetation types compared to peak-summer spectral data. Overall, the proposed framework provides an efficient and interpretable solution for fine-scale estuarine vegetation mapping.
- Top Cited PapersOpen Access
- 17 June 2024
- Published by MDPI AG in Remote Sensing
- Vol. 16 (12) , 2204
Remote Sensing Application in Ecological Restoration Monitoring: A Systematic Review
In the context of the continuous degradation of the global environment, ecological restoration has become a primary task in global environmental governance. In this process, remote sensing technology, as an advanced monitoring and analysis tool, plays a key role in monitoring ecological restoration. This article reviews the application of remote sensing technology in ecological restoration monitoring. Based on a comprehensive analysis of the literature in the field of ecological remote sensing, it systematically summarizes the major in-orbit spaceborne and airborne sensors and their related products. This article further proposes a series of evaluation indicators for ecological restoration from four aspects: forests, soil, water, and the atmosphere, and elaborates on the calculation methods for these indicators. In addition, this paper also summarizes the methods for evaluating the effectiveness of ecological restoration, including subjective evaluation, objective evaluation, and comprehensive evaluation methods. Finally, we analyze the challenges faced by remote sensing technology in evaluating ecological restoration effectiveness, such as issues with the precision of indicators extraction, the limitations of spatial resolution, and the diversity of evaluation methods. This review also looks forward to future ecological restoration technologies, such as the potential applications of integrated aerospace and terrestrial remote sensing, multi-data fusion, and machine learning technologies. This study reveals the effectiveness of remote sensing technology in ecological restoration monitoring, aiming to provide efficient tools and innovative strategies for future remote sensing monitoring and assessment of ecological restoration.
- 17 June 2024
- Published by MDPI AG in Remote Sensing
- Vol. 16 (12) , 2204
Top Cited PapersOpen AccessRemote Sensing Application in Ecological Restoration Monitoring: A Systematic Review
In the context of the continuous degradation of the global environment, ecological restoration has become a primary task in global environmental governance. In this process, remote sensing technology, as an advanced monitoring and analysis tool, plays a key role in monitoring ecological restoration. This article reviews the application of remote sensing technology in ecological restoration monitoring. Based on a comprehensive analysis of the literature in the field of ecological remote sensing, it systematically summarizes the major in-orbit spaceborne and airborne sensors and their related products. This article further proposes a series of evaluation indicators for ecological restoration from four aspects: forests, soil, water, and the atmosphere, and elaborates on the calculation methods for these indicators. In addition, this paper also summarizes the methods for evaluating the effectiveness of ecological restoration, including subjective evaluation, objective evaluation, and comprehensive evaluation methods. Finally, we analyze the challenges faced by remote sensing technology in evaluating ecological restoration effectiveness, such as issues with the precision of indicators extraction, the limitations of spatial resolution, and the diversity of evaluation methods. This review also looks forward to future ecological restoration technologies, such as the potential applications of integrated aerospace and terrestrial remote sensing, multi-data fusion, and machine learning technologies. This study reveals the effectiveness of remote sensing technology in ecological restoration monitoring, aiming to provide efficient tools and innovative strategies for future remote sensing monitoring and assessment of ecological restoration.
- Open Access
- 3 August 2023
- Published by MDPI AG in Remote Sensing
- Vol. 15 (15) , 3859
Application of Deep Learning in Multitemporal Remote Sensing Image Classification
The rapid advancement of remote sensing technology has significantly enhanced the temporal resolution of remote sensing data. Multitemporal remote sensing image classification can extract richer spatiotemporal features. However, this also presents the challenge of mining massive data features. In response to this challenge, deep learning methods have become prevalent in machine learning and have been widely applied in remote sensing due to their ability to handle large datasets. The combination of remote sensing classification and deep learning has become a trend and has developed rapidly in recent years. However, there is a lack of summary and discussion on the research status and trends in multitemporal images. This review retrieved and screened 170 papers and proposed a research framework for this field. It includes retrieval statistics from existing research, preparation of multitemporal datasets, sample acquisition, an overview of typical models, and a discussion of application status. Finally, this paper discusses current problems and puts forward prospects for the future from three directions: adaptability between deep learning models and multitemporal classification, prospects for high-resolution image applications, and large-scale monitoring and model generalization. The aim is to help readers quickly understand the research process and application status of this field.
- 3 August 2023
- Published by MDPI AG in Remote Sensing
- Vol. 15 (15) , 3859
Open AccessApplication of Deep Learning in Multitemporal Remote Sensing Image Classification
The rapid advancement of remote sensing technology has significantly enhanced the temporal resolution of remote sensing data. Multitemporal remote sensing image classification can extract richer spatiotemporal features. However, this also presents the challenge of mining massive data features. In response to this challenge, deep learning methods have become prevalent in machine learning and have been widely applied in remote sensing due to their ability to handle large datasets. The combination of remote sensing classification and deep learning has become a trend and has developed rapidly in recent years. However, there is a lack of summary and discussion on the research status and trends in multitemporal images. This review retrieved and screened 170 papers and proposed a research framework for this field. It includes retrieval statistics from existing research, preparation of multitemporal datasets, sample acquisition, an overview of typical models, and a discussion of application status. Finally, this paper discusses current problems and puts forward prospects for the future from three directions: adaptability between deep learning models and multitemporal classification, prospects for high-resolution image applications, and large-scale monitoring and model generalization. The aim is to help readers quickly understand the research process and application status of this field.