Article
Engineering, Electrical & Electronic
Long Liang, Jing Li, Yunhao Chen, Haiping Xia, Qiang Chen
Summary: The study introduces an auto-adjusted kernel (AAK) method in thermal sharpening, aiming to address the issue of selecting suitable kernels for different windows in OWS and LWS. Experimental results show that the AAK method generally outperforms the FK method, significantly improving accuracy at various downscaling ratios, enhancing accuracy in specific areas, and reducing extreme-value points.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2021)
Review
Remote Sensing
Mohammad Karimi Firozjaei, Majid Kiavarz, Seyed Kazem Alavipanah
Summary: This study comprehensively reviewed Satellite-derived Land Surface Temperature Spatial Sharpening (SLSTSS) studies and provided appropriate solutions for reducing errors in SLSTSS processes. By conducting a thorough search and applying specific criteria, relevant papers were selected and important information was extracted from the assembled database. Several perspectives for future studies were suggested for integrating different models and strategies, solving challenges, considering variables, and providing a physical approach based on energy balance equations for error reduction in SLSTSS processes.
EUROPEAN JOURNAL OF REMOTE SENSING
(2022)
Article
Geography, Physical
Jiameng Lai, Wenfeng Zhan, Jinling Quan, Benjamin Bechtel, Kaicun Wang, Ji Zhou, Fan Huang, Tirthankar Chakraborty, Zihan Liu, Xuhui Lee
Summary: This study proposes a statistical strategy for estimating next-day nighttime Surface Urban Heat Island (SUHI) intensity using a support vector machine regression model. Various SUHI controls were incorporated, leading to estimations for 59 Chinese megacities. The analysis revealed that relative humidity has the greatest contribution to SUHI estimation.
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
(2021)
Article
Engineering, Electrical & Electronic
Yuting Qi, Lei Zhong, Yaoming Ma, Yunfei Fu, Xian Wang, Peizhen Li
Summary: Land surface temperature (LST) is crucial in the Earth's climate system, and its retrieval from satellites is challenging, especially in plateau areas. This study used various methods, including the single channel (SC) algorithm, the split-window (SW) algorithm, and machine learning (ML) models, to improve LST retrieval accuracy over the Tibetan Plateau (TP). The SW algorithm showed better performance, with a lower root-mean-square error (RMSE) of 2.64 K, compared to the official SLSTR LST products (5.23 K), and the random forest model had the highest accuracy with an RMSE of 3.26 K.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2023)
Article
Geography, Physical
Zefeng Xing, Zhao-Liang Li, Si-Bo Duan, Xiangyang Liu, Xiaopo Zheng, Pei Leng, Maofang Gao, Xia Zhang, Guofei Shang
Summary: This study proposes a practical method to estimate daily mean land surface temperature (LST) using MODIS-derived instantaneous LST products, with reliable results validated through in situ measurements. The method is successfully applied to calculate global annual cycle parameters and shows potential for various applications in global LST trend analysis and climate change.
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
(2021)
Article
Engineering, Electrical & Electronic
Wei Wang, Ji Zhou, Xin Wen, Zhiyong Long, Hailing Zhong, Jin Ma, Lirong Ding, Dongmei Qi
Summary: This study develops a novel model based on machine learning techniques to estimate all-weather near-surface air temperature (AW-NSAT). The model, trained with in situ NSAT, shows good accuracy and spatial seamless characteristic by introducing TRIMS LST. It provides the possibility to generate AW-NSAT for the Tibetan Plateau and can be extended to other areas.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2022)
Article
Engineering, Electrical & Electronic
Peifeng Su, Temesgen Abera, Yanlong Guan, Petri Pellikka
Summary: Air temperature at 2 m above the ground (T-a) is crucial for studying earth surface processes. Traditional T-a measurements are limited due to uneven distribution of meteorological stations. Satellite-derived land surface temperature (LST) is commonly used to estimate T-a, but is affected by cloud contamination. To address this, a deep learning method is proposed to estimate seamless T-a from LST with missing values. Experimental results in mainland China show promising accuracy for daily mean, minimum, and maximum T-a with strong linear relationships.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2023)
Article
Environmental Sciences
Qiang Zhang, Zixuan Wu, Vijay P. Singh, Chunling Liu
Summary: This study analyzed data from three urban agglomerations in China over the period 2000-2015, revealing a general rise in land surface temperature attributed to decreased urban green space. The impacts of impervious surface area and urban green space on land surface temperature were found to be more significant than their geometrical shapes. Continuous expansion of impervious surface area and shrinking of urban green space are predicted to drive a rising tendency of land surface temperature, with larger cities showing a larger rising tendency.
Article
Geochemistry & Geophysics
Donghang Wu, Weiquan Liu, Bowen Fang, Linwei Chen, Yu Zang, Lei Zhao, Shenlong Wang, Cheng Wang, Jose Marcato, Jonathan Li
Summary: This article introduces a new approach called PIHP network, which accurately estimates urban surface temperature at high resolution by leveraging the information of land surface structure in high-resolution satellite images. Experiments across different cities in China show the potential of predicting future intracity temperature using this method.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Computer Science, Information Systems
Xiwei Fan, Gaozhong Nie, Yaohui Liu, Li Ni
Summary: A three-channel LST retrieval algorithm was developed to accurately estimate LST in thin cirrus cloudy skies, significantly improving the retrieval accuracy in such conditions. Sensitivity analysis showed that the accuracy of cirrus optical depth (COD) is crucial for LST retrieval. The proposed algorithm outperformed the widely used generalized split-window (GSW) algorithm in cirrus cloudy skies.
Article
Engineering, Electrical & Electronic
Yue Hu, Xinyu Zhou, Ye Zhang, Shaoqi Shi
Summary: A novel subpixel land surface temperature estimation method is proposed in this study, utilizing an information-transfer-based adaptive ensemble extreme learning machine model. It improves spatial resolution of thermal infrared data, reduces the demand for training data, and enables faster and more accurate acquisition of subpixel land surface temperature.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2021)
Article
Environmental Studies
Xin Ye, Rongyuan Liu, Jian Hui, Jian Zhu
Summary: This paper proposes a new algorithm to directly estimate land surface temperature (LST) from Landsat-9 two-channel TIR data without external parameters. The algorithm utilizes ensemble learning method to solve nonlinear problems and considers the physical radiance transfer process. Experimental results show that the algorithm achieves accurate LST estimation results.
Article
Engineering, Electrical & Electronic
Jiaxin Tian, Hui Lu, Kun Yang, Jun Qin, Long Zhao, Yaozhi Jiang, Pengfei Shi, Xiaogang Ma, Jianhong Zhou
Summary: Soil moisture plays a vital role in the global terrestrial water, energy, and carbon cycles. This article develops a novel land surface temperature assimilation scheme, which improves soil moisture estimation accuracy by linking simulated ensembles of soil moisture with remote sensing land surface temperature.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2023)
Article
Geochemistry & Geophysics
Huazhong Ren, Xin Ye, Jing Nie, Jinjie Meng, Wenjie Fan, Qiming Qin, Yanzhen Liang, Hongcheng Liu
Summary: A novel feature-band linear-format hybrid (FebLihy) algorithm combining deep neural network (DNN) model and physical model was proposed for simultaneous retrieval of atmospheric parameters, land surface temperature (LST), and emissivity from thermal hyperspectral remote sensing data. The algorithm showed promising results in terms of accuracy and effectiveness in both simulation and real data experiments. Future studies will focus on further optimizing the model and data for improved performance.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Environmental Sciences
Bing Li, Shunlin Liang, Xiaobang Liu, Han Ma, Yan Chen, Tianchen Liang, Tao He
Summary: This study proposes a methodology for generating all-sky Land Surface Temperature (LST) products by combining multiple datasets, showing strong model stability and producing more accurate spatial patterns over the contiguous United States compared to existing products.
REMOTE SENSING OF ENVIRONMENT
(2021)
Article
Engineering, Civil
Wentao Li, Baoxiang Pan, Jiangjiang Xia, Qingyun Duan
Summary: Raw forecasts from numerical weather prediction models can have bias and limited spatial information. This paper proposes a CNN-based post-processing method for precipitation forecasts that utilizes spatial information and atmospheric circulation variables. The results show that the proposed CNN-based model outperforms traditional methods and other neural network models in terms of forecast accuracy and reliability, especially for heavy rain.
JOURNAL OF HYDROLOGY
(2022)
Article
Meteorology & Atmospheric Sciences
Zhu Liu, Qingyun Duan, Xuewei Fan, Wentao Li, Jina Yin
Summary: The Pan Third Pole (PTP) region is one of the most sensitive places on earth to climate change. This study evaluates the historical precipitation and temperature changes in the PTP region using 16 model predictions from CMIP6 and CRU observations. The results show that temperature is underestimated while precipitation is overestimated in the region. The Bayesian model averaging approach provides more reliable predictions, indicating that the region will become warmer and wetter in the future, especially under the SSP5-8.5 scenario.
Article
Environmental Sciences
Shuaijun Liu, Junxiong Zhou, Yuean Qiu, Jin Chen, Xiaolin Zhu, Hui Chen
Summary: Spatiotemporal fusion is an important tool for monitoring land surface dynamics, but existing methods ignore the spectral autocorrelation information. In this study, a novel spatiotemporal fusion method that fully utilizes the multiple spectral bands is proposed.
REMOTE SENSING OF ENVIRONMENT
(2022)
Article
Geography, Physical
Yunze Zang, Yuean Qiu, Xuehong Chen, Jin Chen, Wei Yang, Yifei Liu, Longkang Peng, Miaogen Shen, Xin Cao
Summary: RSG-OC is an automated rapeseed mapping approach that combines rule-based sample generation and a one-class classifier (PUL-RF). It generates cloud-free samples during the predicted flowering period using empirical index-based sample selection rules, utilizes all available features based on the rapeseed phenological calendar for classification, and improves generalization to pixels without cloud-free observations using a specific sample augmentation. The method achieved a high accuracy of 94.90% in mapping rapeseed in China.
GISCIENCE & REMOTE SENSING
(2023)
Article
Environmental Sciences
Shuai Xu, Xiaolin Zhu, Jin Chen, Xuelin Zhu, Mingjie Duan, Bingwen Qiu, Luoma Wan, Xiaoyue Tan, Yi Nam Xu, Ruyin Cao
Summary: Timely and accurate mapping of paddy rice cultivation is crucial for sustainable rice production, food security, and water usage monitoring. This study proposes a new SAR-based Paddy Rice Index (SPRI) to quantify the probability of land patches planted with paddy rice. The SPRI method outperforms existing methods in heterogeneous agricultural areas, producing accurate classification maps for large areas, especially in cloudy regions.
REMOTE SENSING OF ENVIRONMENT
(2023)
Article
Environmental Sciences
Na Jie, Xin Cao, Jin Chen, Xuehong Chen
Summary: Central business districts (CBDs) are crucial in urban economic activities, but there is currently no automated standardization technique for identifying and delineating CBDs worldwide. This paper proposes a new method based on nighttime lights (NTL) to overcome this limitation. The method uses high-quality global Black Marble products and considers CBD characteristics such as brightness and NTL negative angular effects. The method was successfully employed in 14 cities in China and the U.S., highlighting its potential for CBD detection and delineation over large areas.
Article
Water Resources
Wen-tao Li, Jia-peng Zhang, Ruo-chen Sun, Qingyun Duan
Summary: The extreme rainfall event in Henan Province, China in July 2021 caused severe urban waterlogging and floods. This study evaluated the performance of high-resolution weather forecasts in predicting the event and investigated the feasibility of weather forecast-based hydrological forecasts. Results showed that the Tianji weather system accurately predicted precipitation amplitudes and had closer rainfall location and structure to observations compared to the ECMWF forecast system. The hydrological model driven by Tianji weather forecasts effectively predicted the extreme flood event and outperformed the ECMWF-driven model in terms of amplitude and location.
WATER SCIENCE AND ENGINEERING
(2023)
Article
Environmental Sciences
Ruilin Chen, Xiaoyue Tan, Yuanming Zhang, Hui Chen, Benfeng Yin, Xiaolin Zhu, Jin Chen
Summary: This study investigates the potential of using the spectral response of biocrusts to monitor rainfall events in desert areas. The results show that rainfall events induce significant changes in biocrust spectra, and a random forest model performs better than mainstream precipitation products in temporal monitoring and spatial pattern delineation of rainfall events.
REMOTE SENSING OF ENVIRONMENT
(2023)
Article
Meteorology & Atmospheric Sciences
Nan Jiang, Miaogen Shen, Jin Chen, Wei Yang, Xiaolin Zhu, Xufeng Wang, Josep Penuelas
Summary: Previous studies have shown a significant advance in vegetation green-up (VGD) onset date in the Northern Hemisphere during the 1980s and 1990s. However, later studies based on advanced very high-resolution radiometer (AVHRR) data suggested a hiatus in this trend during the warming period from the late 1990s to early 2010s. There is uncertainty in this finding due to quality issues associated with AVHRR data. Our study, using high-quality Moderate Resolution Imaging Spectroradiometer data, shows that VGD advanced significantly despite the warming hiatus, suggesting caution in inferring climate warming based on spring phenology advances.
NPJ CLIMATE AND ATMOSPHERIC SCIENCE
(2023)
Article
Multidisciplinary Sciences
Xining Zhang, Yong Ge, Jin Chen, Feng Ling, Qunming Wang, Delin Du, Ru Xiang
Summary: Super-resolution mapping (SRM) is an important technology in remote sensing. To address the issues of existing models that only focus on spectral features, we propose a soft information-constrained network (SCNet) that leverages soft information as a spatial prior. SCNet generates more complete spatial details in complex areas, providing an effective means for producing high-quality and high-resolution mapping products from remote sensing images.
Article
Biodiversity Conservation
Licong Liu, Jin Chen, Miaogen Shen, Xuehong Chen, Ruyin Cao, Xin Cao, Xihong Cui, Wei Yang, Xiaolin Zhu, Le Li, Yanhong Tang
Summary: We propose a novel method for remotely sensing alpine grasslines and determining their positions, which is of great importance for investigating the response of alpine grasslands to climate change.
GLOBAL CHANGE BIOLOGY
(2023)
Editorial Material
Multidisciplinary Sciences
Brooks Hanson, Shelley Stall, Joel Cutcher-Gershenfeld, Kristina Vrouwenvelder, Christopher Wirz, Yuhan (Douglas) Rao, Ge Peng
Summary: AI tools are transforming data-driven science, but better ethical standards and data management are needed to support its growth and prevent issues.
Article
Environmental Sciences
Zhiguang Chen, Miaogen Shen, Nan Jiang, Jin Chen, Yanhong Tang, Song Gu
Summary: Daytime warming can delay the end of the vegetation growing season on the Tibetan Plateau, despite the inhibitory effect of low temperatures on alpine vegetation activity. Researchers should take into account the interactive effects of temperature and precipitation on the timing of the growing season when modeling autumn phenology in this region.
SCIENCE OF THE TOTAL ENVIRONMENT
(2023)
Article
Hospitality, Leisure, Sport & Tourism
Luning Li, Zixuan Pei, Qiang Li, Fengxin Hao, Xiang Chen, Jin Chen
Summary: This study proposes a new method called the stay-time-based tourism attractiveness index (STTAI) to identify tourism attractiveness within a destination using Wi-Fi data. The study tracked Wi-Fi probe requests from 670,000 travelers over a month in the Shichahai scenic area and employed the STTAI to identify locations with high tourism attractiveness. Regression analysis was also used to examine the environmental impact on identified tourism attractiveness.
CURRENT ISSUES IN TOURISM
(2023)
Article
Geochemistry & Geophysics
Xue Yang, Jin Chen, Qingfeng Guan, Huan Gao, Wei Xia
Summary: This study proposes an enhanced method called cuSTSG, based on the spatial-temporal Savitzky-Golay (STSG) method, to address noise reduction in NDVI time-series data. cuSTSG effectively generates high-quality and accurate NDVI time-series data by improving the accuracy of quality flags and optimizing computational performance.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)