Longlong ZHAO

Dr. Longlong ZHAO

Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, Guangdong, China
orcid
Associate Research Fellow

Research Focus & Metrics

Academic Career Length

15Years (2012-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 October 2014 in Quaternary International
Verified
Journal Article
Closed access
LWLili Wang
Lili Wang
MTMingzhong Tian
Mingzhong Tian
XWXuefeng Wen
Xuefeng Wen
Longlong ZHAOLonglong ZHAO
Longlong ZHAO
JSJiling Song
Jiling Song
MSMiao Sun
Miao Sun

1 November 2020 in Agriculture, Ecosystems & Environment
Verified
Journal Article
Closed access
Longlong ZHAOLonglong ZHAO
Longlong ZHAO
Wenjiang HuangWenjiang Huang
Wenjiang Huang
JCJinsong Chen
Jinsong Chen
YDYingying Dong
Yingying Dong
BRBinyuan Ren
Binyuan Ren
YGYun Geng
Yun Geng

6 December 2024 in Remote Sensing
Verified
Journal Article
Open access
PDF file
Zhengxin WangZhengxin Wang
Zhengxin Wang
Longlong ZHAOLonglong ZHAO
Longlong ZHAO
JMJintao Meng
Jintao Meng
YHYu Han
Yu Han
XLXiaoli Li
Xiaoli Li
HLHongzhong Li
Hongzhong Li
In optical remote sensing images, the presence of clouds affects the completeness of the ground observation and further affects the accuracy and efficiency of remote sensing applications. Especially in quantitative analysis, the impact of cloud cover on the reliability of analysis results cannot be ignored. Therefore, high-precision cloud detection is an important step in the preprocessing of optical remote sensing images. In the past decade, with the continuous progress of artificial intelligence, algorithms based on deep learning have become one of the main methods for cloud detection. The rapid development of deep learning technology, especially the introduction of self-attention Transformer models, has greatly improved the accuracy of cloud detection tasks while achieving efficient processing of large-scale remote sensing images. This review provides a comprehensive overview of cloud detection algorithms based on deep learning from the perspective of semantic segmentation, and elaborates on the research progress, advantages, and limitations of different categories in this field. In addition, this paper introduces the publicly available datasets and accuracy evaluation indicators for cloud detection, compares the accuracy of mainstream deep learning models in cloud detection, and briefly summarizes the subsequent processing steps of cloud shadow detection and removal. Finally, this paper analyzes the current challenges faced by existing deep learning-based cloud detection algorithms and the future development direction of the field.

5 February 2022 in Remote Sensing
Verified
Journal Article
Open access
PDF file
RSRuiqi Sun
Ruiqi Sun
Wenjiang HuangWenjiang Huang
Wenjiang Huang
YDYingying Dong
Yingying Dong
Longlong ZHAOLonglong ZHAO
Longlong ZHAO
Biyao ZhangBiyao Zhang
Biyao Zhang
XLXueling Li
Xueling Li
Desert locust plagues can easily cause a regional food crisis and thus affect social stability. Preventive control of the disaster highlights the early detection of hopper gregarization before they form devastating swarms. However, the response of hopper band emergence to environmental fluctuation exhibits a time lag. To realize the dynamic forecast of band occurrence with optimal temporal predictors, we proposed an SVM-based model with a temporal sliding window technique by coupling multisource time-series imagery with historical locust ground survey observations from between 2000–2020. The sliding window method was based on a lagging variable importance ranking used to analyze the temporal organization of environmental indicators in band-forming sequences and eventually facilitate the early prediction of band emergence. Statistical results show that hopper bands are more likely to occur within 41–64 days after increased rainfall; soil moisture dynamics increasing by approximately 0.05 m³/m³ then decreasing may enhance the chance of observing bands after 73–80 days. While sparse vegetation areas with NDVI increasing from 0.18 to 0.25 tend to witness bands after 17–40 days. The forecast model combining the optimal time lags of these dynamic indicators with other static indicators allows for a 16-day extended outlook of band presence in Somalia, Ethiopia, and Kenya. Monthly predictions from February to December 2020 display an overall accuracy of 77.46%, with an average ROC-AUC of 0.767 and a mean F-score close to 0.772. The multivariate forecast framework based on the lagging effect can realize the early warning of band presence in different spatiotemporal scenarios, supporting early decisions and response strategies for desert locust preventive management.

8 March 2023 in Land
Verified
Journal Article
Open access
PDF file
YGYuankai Ge
Yuankai Ge
Longlong ZHAOLonglong ZHAO
Longlong ZHAO
Jinsong ChenJinsong Chen
Jinsong Chen
XLXiaoli Li
Xiaoli Li
HLHongzhong Li
Hongzhong Li
YRYanni Ren
Yanni Ren
Soil erosion often leads to land degradation, agricultural production reduction, and environmental deterioration, which seriously restricts the sustainable development of regions. Clarifying the driving factors of soil erosion is the premise of preventing soil erosion. Given the lack of current research on the driving factors/force changes of soil erosion in different regions or under different erosion intensity grades, this paper pioneered to use machine learning methods to address this problem. Firstly, the widely used (Revised) Universal Soil Loss Equation ((R)USLE) framework was applied to simulate the spatial distribution of soil erosion. Then, the K-fold algorithm was used to evaluate the accuracy and stability of five machine learning algorithms for fitting soil erosion. The random forest (RF) method performed best, with average accuracy reaching 86.35%. Then, the Permutation Importance (PI) and the Partial Dependence Plot (PDP) methods based on RF were introduced to quantitatively analyze the main driving factors under different geological conditions and the driving force changes of each factor under different erosion intensity grades, respectively. Results showed that the main drivers of soil erosion in Chongqing and Guizhou were cover management factors (PI: 0.4672, 0.4788), while that in Sichuan was slope length and slope factor (PI: 0.6165). Under different erosion intensity grades, the driving force of each factor shows nonlinear and complex inhibitory or promoting effects with factor value changing. These findings can provide scientific guidance for the refined management of soil erosion, which is significant for halting or reversing land degradation and achieving sustainable use of land resources.

10 September 2020 in IEEE Access
Verified
Journal Article
Open access
YGYun Geng
Yun Geng
Longlong ZHAOLonglong ZHAO
Longlong ZHAO
YDYingying Dong
Yingying Dong
WHWenjiang Huang
Wenjiang Huang
YSYue Shi
Yue Shi
BRBinyuan Ren
Binyuan Ren
The outbreak of Oriental Migratory Locust(Locusta migratoria manilensis) causes devastating disasters to agriculture. With the impact of climate changes and human activities, the distribution of locust habitat (locust habitat is the environment in which locusts live and survive) in China is constantly changing. Monitoring and extracting locust habitat are of great significance for guiding largescale agricultural production. The occurrence of the locust is closely related to their habitat. Therefore, a comprehensive analysis of habitat factors that affect locust survival is carried out to monitor locust habitat distribution. Besides, the landscape structure also affects distribution. This study explored a model for analyzing multi-temporal Landsat and MODIS images, which combined multiple habitat factors and landscape structure to analyze locust habitat. The locust habitat near North Dagang Reservoir in Tianjin is the research object. First, the habitat factors that affect locust oviposition and growth were analyzed, and vegetation coverage, land cover class, soil moisture, soil salinity, and land surface temperature were selected as five habitat factors. The weights of five habitat factors were evaluated according to the Analytic Hierarchy Process (AHP) model. Then, considering the impact of landscape structure on locust habitat, a moving-window was used to correlate locust habitat factors at pixel scale with locust habitat at patch scale. Finally, the distribution map of the locust habitat at patch scale was generated. The Analytic Hierarchy Process(AHP) was used to compare and test the results. Our research shows that the Patch based - Analytic Hierarchy Process (PB-AHP) can monitor locust habitat. The overall accuracy reached 88%, which is 10% higher than the result based on the Analytic Hierarchy Process(AHP). These results show that the Patch based - Analytic Hierarchy Process (PB-AHP) model has strong robustness and generalization ability in identifying locust habitat and can provide scientific guidance for locust monitoring and control.