Qifeng Zhuang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Qifeng Zhuang has a total of 46 co-authors. Here are the top co-authors by number of shared publications:
Weiwei Zhu
4 shared publicationsBingfang Wu
Key Laboratory of Digital Earth Science, Institute of Remote Sensing and Digital Earth (RADI), Chinese Academy of Sciences, Beijing 100094, China
3 shared publications- Dong Chen
College of Geomatics Science and Technology, Nanjing Tech University, Nanjing 211816, China
3 shared publications Nana Yan
Key Laboratory of Digital Earth Science, Institute of Remote Sensing and Digital Earth (RADI), Chinese Academy of Sciences, Beijing 100094, China
3 shared publications- Bingfang Wu
Aerospace Information Research Institute, Chinese Academy of Sciences
2 shared publications - Hua Shao
School of Geomatics Science and Technology, Nanjing Tech University, Nanjing, China
2 shared publications
Latest Publications
- Open Access
- 22 October 2025
- Published by MDPI AG in Agriculture
- Vol. 15 (21) , 2193
An Interpretable Machine Learning Approach to Remote Sensing-Based Estimation of Hourly Agricultural Evapotranspiration in Drylands
Obtaining evapotranspiration (ET) estimates at high spatiotemporal resolution is a fundamental prerequisite for clarifying the patterns and controlling factors of agricultural water consumption in drylands. However, most existing ET products are provided at daily or coarser spatial–temporal scales, which limits the ability to capture short-term variations in crop water use. This study developed a novel hourly 10-m ET estimation method that combines remote sensing with machine learning techniques. The approach was evaluated using agricultural sites in two arid regions: the Heihe River Basin in China and the Bekaa Valley in Lebanon. By integrating hourly eddy covariance measurements, Sentinel-2 reflectance data, and ERA5-Land reanalysis meteorological variables, we constructed an XGBoost-based modeling framework for hourly ET estimation, and incorporated the SHapley Additive exPlanations (SHAP) method for model interpretability analysis. Results demonstrated that the model achieved strong performance across all sites (R2 = 0.86–0.91, RMSE = 0.04–0.05 mm·h−1). Additional metrics, including the Nash–Sutcliffe efficiency coefficient (NSE) and percent bias (PBIAS), further confirmed the model’s robustness. Interpreting the model with SHAP highlighted net radiation (Rn), 2-m temperature (t2m), and near-infrared reflectance of vegetation (NIRv) as the dominant factors controlling hourly ET variations. Significant interaction effects, such as Rn × NIRv and Rn × t2m, were also identified, revealing the modulation mechanism of energy, vegetation status and temperature coupling on hourly ET. The study offers a practical workflow and an interpretable framework for generating high-resolution ET maps, thereby supporting regional water accounting and land–atmosphere interaction research.
- 22 October 2025
- Published by MDPI AG in Agriculture
- Vol. 15 (21) , 2193
Open AccessAn Interpretable Machine Learning Approach to Remote Sensing-Based Estimation of Hourly Agricultural Evapotranspiration in Drylands
Obtaining evapotranspiration (ET) estimates at high spatiotemporal resolution is a fundamental prerequisite for clarifying the patterns and controlling factors of agricultural water consumption in drylands. However, most existing ET products are provided at daily or coarser spatial–temporal scales, which limits the ability to capture short-term variations in crop water use. This study developed a novel hourly 10-m ET estimation method that combines remote sensing with machine learning techniques. The approach was evaluated using agricultural sites in two arid regions: the Heihe River Basin in China and the Bekaa Valley in Lebanon. By integrating hourly eddy covariance measurements, Sentinel-2 reflectance data, and ERA5-Land reanalysis meteorological variables, we constructed an XGBoost-based modeling framework for hourly ET estimation, and incorporated the SHapley Additive exPlanations (SHAP) method for model interpretability analysis. Results demonstrated that the model achieved strong performance across all sites (R2 = 0.86–0.91, RMSE = 0.04–0.05 mm·h−1). Additional metrics, including the Nash–Sutcliffe efficiency coefficient (NSE) and percent bias (PBIAS), further confirmed the model’s robustness. Interpreting the model with SHAP highlighted net radiation (Rn), 2-m temperature (t2m), and near-infrared reflectance of vegetation (NIRv) as the dominant factors controlling hourly ET variations. Significant interaction effects, such as Rn × NIRv and Rn × t2m, were also identified, revealing the modulation mechanism of energy, vegetation status and temperature coupling on hourly ET. The study offers a practical workflow and an interpretable framework for generating high-resolution ET maps, thereby supporting regional water accounting and land–atmosphere interaction research.
- Open Access
- 30 May 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (11) , 6202
Generating 1 km Seamless Land Surface Temperature from China FY3C Satellite Data Using Machine Learning
Land Surface Temperature (LST), as a core variable in the coupling of land–atmosphere energy transfers and ecological responses, relies heavily on the global coverage capacity of thermal infrared remote sensing (TIR-LST) for dynamic monitoring. Currently, the time reconstruction method of the TIR-LST products from China’s Fengyun polar-orbiting satellite under dynamic cloud interference remains under exploration. This study focuses on the Heihe River Basin in western China, and addresses the issue of cloud coverage in relation to the Fengyun-3C (FY-3C) satellite TIR-LST. An innovative spatiotemporal reconstruction framework based on multi-source data collaboration was developed. Using a hybrid ensemble learning framework of random forest and ridge regression, environmental parameters such as vegetation index (NDVI), land cover type (LC), digital elevation model (DEM), and terrain slope were integrated. A downscaling and multi-factor collaborative representation model for land surface temperature was constructed, thereby integrating the passive microwave LST and thermal infrared VIRR-LST from the FY-3C satellite. This produced a seamless LST dataset with 1 km resolution for the period of 2017–2019, with temporal continuity across space. The validation results show that the reconstructed data significantly improves accuracy compared to the original VIRR-LST and demonstrates notable spatiotemporal consistency with MODIS LST at the daily scale (annual R2 ≥ 0.88, RMSE < 2.3 K). This method successfully reconstructed the FY-3C satellite’s 1 km level all-weather LST time series, providing reliable technical support for the use of domestic satellite data in remote sensing applications such as ecological drought monitoring and urban heat island tracking.
- 30 May 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (11) , 6202
Open AccessGenerating 1 km Seamless Land Surface Temperature from China FY3C Satellite Data Using Machine Learning
Land Surface Temperature (LST), as a core variable in the coupling of land–atmosphere energy transfers and ecological responses, relies heavily on the global coverage capacity of thermal infrared remote sensing (TIR-LST) for dynamic monitoring. Currently, the time reconstruction method of the TIR-LST products from China’s Fengyun polar-orbiting satellite under dynamic cloud interference remains under exploration. This study focuses on the Heihe River Basin in western China, and addresses the issue of cloud coverage in relation to the Fengyun-3C (FY-3C) satellite TIR-LST. An innovative spatiotemporal reconstruction framework based on multi-source data collaboration was developed. Using a hybrid ensemble learning framework of random forest and ridge regression, environmental parameters such as vegetation index (NDVI), land cover type (LC), digital elevation model (DEM), and terrain slope were integrated. A downscaling and multi-factor collaborative representation model for land surface temperature was constructed, thereby integrating the passive microwave LST and thermal infrared VIRR-LST from the FY-3C satellite. This produced a seamless LST dataset with 1 km resolution for the period of 2017–2019, with temporal continuity across space. The validation results show that the reconstructed data significantly improves accuracy compared to the original VIRR-LST and demonstrates notable spatiotemporal consistency with MODIS LST at the daily scale (annual R2 ≥ 0.88, RMSE < 2.3 K). This method successfully reconstructed the FY-3C satellite’s 1 km level all-weather LST time series, providing reliable technical support for the use of domestic satellite data in remote sensing applications such as ecological drought monitoring and urban heat island tracking.
- Open Access
Assessing a machine learning-based downscaling framework for obtaining 1km daily precipitation from GPM data
- Open Access
- 22 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 103274-103287
Generating Daily Gap-Free MODIS Land Surface Temperature Using the Random Forest Model and Similar Pixels Method
The land surface temperature (LST) is one of the vital variables for surface-atmosphere interaction. However, due to the vulnerability of thermal infrared remote sensing to clouds, the MODIS LST products have many observation gaps, which seriously limits their application. In this paper, to make up for the shortage of random forest model in reconstructing images with substantial cloud-cover pixels, a combined random forest (RF) and similar pixels (SP) reconstruction scheme was proposed to generate daily gap-free MODIS/Terra LST product and validated by the automatic weather stations (AWS) data in the Heihe River Basin. First, we used the RF model to reconstruct the images that meet the threshold (the clear-sky pixels percentage is more than 30%). Then, we used a combination of the RF model and the SP method to reconstruct the images that do not meet the threshold. Thus, the daily MODIS LST reconstruction results were obtained. The visual assessment indicated that the reconstructed LST strongly correlates with the original LST and can capture the spatial distribution features of LST-related characteristic variables. Additionally, the validation with in situ observations demonstrated that the method of directly using the RF model performs well with an R 2 of 0.87, an NSE of 0.87, an RMSE, and a Bias of 4.69 K and 0.08 K, respectively. The RF model and SP method combination still have a good performance with an R 2 of 0.79, an NSE of 0.76, and an RMSE and Bias of 6.37 K and 0.62 K, respectively.
- 22 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 103274-103287
Open AccessGenerating Daily Gap-Free MODIS Land Surface Temperature Using the Random Forest Model and Similar Pixels Method
The land surface temperature (LST) is one of the vital variables for surface-atmosphere interaction. However, due to the vulnerability of thermal infrared remote sensing to clouds, the MODIS LST products have many observation gaps, which seriously limits their application. In this paper, to make up for the shortage of random forest model in reconstructing images with substantial cloud-cover pixels, a combined random forest (RF) and similar pixels (SP) reconstruction scheme was proposed to generate daily gap-free MODIS/Terra LST product and validated by the automatic weather stations (AWS) data in the Heihe River Basin. First, we used the RF model to reconstruct the images that meet the threshold (the clear-sky pixels percentage is more than 30%). Then, we used a combination of the RF model and the SP method to reconstruct the images that do not meet the threshold. Thus, the daily MODIS LST reconstruction results were obtained. The visual assessment indicated that the reconstructed LST strongly correlates with the original LST and can capture the spatial distribution features of LST-related characteristic variables. Additionally, the validation with in situ observations demonstrated that the method of directly using the RF model performs well with an R 2 of 0.87, an NSE of 0.87, an RMSE, and a Bias of 4.69 K and 0.08 K, respectively. The RF model and SP method combination still have a good performance with an R 2 of 0.79, an NSE of 0.76, and an RMSE and Bias of 6.37 K and 0.62 K, respectively.
- Open Access
- 11 August 2023
- Published by MDPI AG in Agriculture
- Vol. 13 (8) , 1592
Mapping Cropland Soil Nutrients Contents Based on Multi-Spectral Remote Sensing and Machine Learning
Nitrogen (N) and phosphorus (P) are primary indicators of soil nutrients in agriculture. Accurate management of these nutrients is essential for ensuring food security. High-resolution, multi-spectral remote sensing images can provide crucial information for mapping soil nutrients at the field scale. This study compares the capabilities of ZH-1 and Sentinel-2 satellite data, along with different spectral indices, in mapping soil nutrients (total N and Olsen-P) using two machine learning algorithms, random forest (RF) and XGBoost (XGB). Two agricultural fields in Suihua City were selected as the study areas for this investigation. The results showed that Sentinel-2 data performed best in computing the total N content in soil using the RF model (R2 = 0.74, RMSE = 0.10 g/kg). However, for the soil Olsen-P content, the XGBoost model performed better with ZH-1 data (R2 = 0.75, RMSE = 9.79 mg/kg) than the RF model. This study demonstrates that both ZH-1 and Sentinel-2 satellite data perform well in terms of accurately mapping soil total N and Olsen-P contents using machine learning. Due to its higher spectral and spatial resolution, ZH-1 remote sensing data provides more detailed information on soil nutrient content during Olsen-P inversion and exhibits comparable accuracy.
- 11 August 2023
- Published by MDPI AG in Agriculture
- Vol. 13 (8) , 1592
Open AccessMapping Cropland Soil Nutrients Contents Based on Multi-Spectral Remote Sensing and Machine Learning
Nitrogen (N) and phosphorus (P) are primary indicators of soil nutrients in agriculture. Accurate management of these nutrients is essential for ensuring food security. High-resolution, multi-spectral remote sensing images can provide crucial information for mapping soil nutrients at the field scale. This study compares the capabilities of ZH-1 and Sentinel-2 satellite data, along with different spectral indices, in mapping soil nutrients (total N and Olsen-P) using two machine learning algorithms, random forest (RF) and XGBoost (XGB). Two agricultural fields in Suihua City were selected as the study areas for this investigation. The results showed that Sentinel-2 data performed best in computing the total N content in soil using the RF model (R2 = 0.74, RMSE = 0.10 g/kg). However, for the soil Olsen-P content, the XGBoost model performed better with ZH-1 data (R2 = 0.75, RMSE = 9.79 mg/kg) than the RF model. This study demonstrates that both ZH-1 and Sentinel-2 satellite data perform well in terms of accurately mapping soil total N and Olsen-P contents using machine learning. Due to its higher spectral and spatial resolution, ZH-1 remote sensing data provides more detailed information on soil nutrient content during Olsen-P inversion and exhibits comparable accuracy.
- Open Access
- 15 June 2022
- Published by MDPI AG in Applied Sciences
- Vol. 12 (12) , 6068
Comparison of Methods for Reconstructing MODIS Land Surface Temperature under Cloudy Conditions
Land surface temperature (LST) is a vital parameter associated with the land–atmosphere interface. The Moderate Resolution Imaging Spectroradiometer (MODIS) LST product can provide precise LST with high time resolution, and is widely applied in various remote sensing temperature research. However, due to its inability to penetrate the cloud and fog, its quality is not able to meet the requirements of actual research. Hence, obtaining continuous and cloudless MODIS LST datasets remains challenging for researchers. The critical point is to reconstruct missing pixels. To compare the performance of different methods, first, three kinds of methods were used to reconstruct the missing pixels, namely, temporal, spatial, and spatiotemporal methods. The predicted values using these methods were validated by the automatic weather system data (AWS) in the Heihe river basin of China. The results demonstrated that, compared with other methods, linear temporal interpolation using Aqua data had the best performance in MODIS LST reconstruction in the Heihe river basin, with an RMSE of 7.13 K and an R2 of 0.82, and the NSE and PBias were 0.78 and −0.76%, respectively. Furthermore, the interpolation method was improved using adaptive windows and robust regression. First, the international Geosphere–Biosphere Program (IGBP) classification was employed to distinguish the different land surface types. Then, the invalid LST values were reconstructed using adjacent days’ effective LST values combined with a robust regression. Finally, a mean filter was applied to eliminate outliers. The overall results combined with ERA5 data were validated by AWS, with an RMSE of 6.96 K and an R2 of 0.79 and the NSE and PBias were 0.77 and −0.20%, respectively. The validation demonstrated that the scheme proposed in this paper is able to accurately reconstruct the missing values and improve the accuracy of the interpolation method to a certain extent when reconstructing MODIS LST.
- 15 June 2022
- Published by MDPI AG in Applied Sciences
- Vol. 12 (12) , 6068
Open AccessComparison of Methods for Reconstructing MODIS Land Surface Temperature under Cloudy Conditions
Land surface temperature (LST) is a vital parameter associated with the land–atmosphere interface. The Moderate Resolution Imaging Spectroradiometer (MODIS) LST product can provide precise LST with high time resolution, and is widely applied in various remote sensing temperature research. However, due to its inability to penetrate the cloud and fog, its quality is not able to meet the requirements of actual research. Hence, obtaining continuous and cloudless MODIS LST datasets remains challenging for researchers. The critical point is to reconstruct missing pixels. To compare the performance of different methods, first, three kinds of methods were used to reconstruct the missing pixels, namely, temporal, spatial, and spatiotemporal methods. The predicted values using these methods were validated by the automatic weather system data (AWS) in the Heihe river basin of China. The results demonstrated that, compared with other methods, linear temporal interpolation using Aqua data had the best performance in MODIS LST reconstruction in the Heihe river basin, with an RMSE of 7.13 K and an R2 of 0.82, and the NSE and PBias were 0.78 and −0.76%, respectively. Furthermore, the interpolation method was improved using adaptive windows and robust regression. First, the international Geosphere–Biosphere Program (IGBP) classification was employed to distinguish the different land surface types. Then, the invalid LST values were reconstructed using adjacent days’ effective LST values combined with a robust regression. Finally, a mean filter was applied to eliminate outliers. The overall results combined with ERA5 data were validated by AWS, with an RMSE of 6.96 K and an R2 of 0.79 and the NSE and PBias were 0.77 and −0.20%, respectively. The validation demonstrated that the scheme proposed in this paper is able to accurately reconstruct the missing values and improve the accuracy of the interpolation method to a certain extent when reconstructing MODIS LST.
- Open Access
- 19 May 2022
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 17 (5) , e0267811
Estimation of Landsat-like daily evapotranspiration for crop water consumption monitoring using TSEB model and data fusion
Evapotranspiration (ET) plays an essential role in agricultural water resource management. Understanding regional agricultural water consumption characteristics can be improved by predicting ET using remote sensing. However, due to the lack of high-resolution images on clear-sky days or the limitation of ET reconstruction on cloudy-sky days, it remains challenging to continuously derive ET at the field scale. In this study, the Landsat and MODIS data were initially fused to obtain the Landsat-like vegetation index and land surface temperature on clear-sky days. Then the two-source energy balance (TSEB) model was applied to calculate the daily ET during the clear-sky. A canopy resistance-based gap-filling method was involved in reconstructing regional ET on cloudy days while considering different environmental factors. The estimations were validated by automatic weather system data (AWS) and eddy covariance (EC) measurements in Guantao County. The results demonstrated that the proposed scheme performed well in estimating cropland ET, with an RMSE of 0.86 mm·d−1 and an R2 of 0.65, and the NSE and PBias were 0.61 and -0.29%, respectively. The crop water consumption analysis revealed that the daily ET of winter wheat peaked during the maturation stage. Nevertheless, summer maize water consumption peaked in the middle of the growing season in this area. The temperature during the early development stage and the soil moisture in the mid and late growth stages had the greatest impact on the ET of winter wheat. During the entire growing period, soil moisture had the largest effect on the ET of summer maize. The findings showed that the TSEB model can be effectively applied to field-scale water consumption monitoring in North China through MODIS and Landsat data fusion and ET temporal reconstruction considering environmental factors.
- 19 May 2022
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 17 (5) , e0267811
Open AccessEstimation of Landsat-like daily evapotranspiration for crop water consumption monitoring using TSEB model and data fusion
Evapotranspiration (ET) plays an essential role in agricultural water resource management. Understanding regional agricultural water consumption characteristics can be improved by predicting ET using remote sensing. However, due to the lack of high-resolution images on clear-sky days or the limitation of ET reconstruction on cloudy-sky days, it remains challenging to continuously derive ET at the field scale. In this study, the Landsat and MODIS data were initially fused to obtain the Landsat-like vegetation index and land surface temperature on clear-sky days. Then the two-source energy balance (TSEB) model was applied to calculate the daily ET during the clear-sky. A canopy resistance-based gap-filling method was involved in reconstructing regional ET on cloudy days while considering different environmental factors. The estimations were validated by automatic weather system data (AWS) and eddy covariance (EC) measurements in Guantao County. The results demonstrated that the proposed scheme performed well in estimating cropland ET, with an RMSE of 0.86 mm·d−1 and an R2 of 0.65, and the NSE and PBias were 0.61 and -0.29%, respectively. The crop water consumption analysis revealed that the daily ET of winter wheat peaked during the maturation stage. Nevertheless, summer maize water consumption peaked in the middle of the growing season in this area. The temperature during the early development stage and the soil moisture in the mid and late growth stages had the greatest impact on the ET of winter wheat. During the entire growing period, soil moisture had the largest effect on the ET of summer maize. The findings showed that the TSEB model can be effectively applied to field-scale water consumption monitoring in North China through MODIS and Landsat data fusion and ET temporal reconstruction considering environmental factors.
- Open Access
- 17 February 2022
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 17 (2) , e0264133
Operational daily evapotranspiration mapping at field scale based on SSEBop model and spatiotemporal fusion of multi-source remote sensing data
Accurate understanding of daily evapotranspiration (ET) at field scale is of great significance for agricultural water resources management. The operational simplified surface energy balance (SSEBop) model has been applied to estimate field scale ET with Landsat satellite imagery. However, there is still uncertainty in the ET time reconstruction for cloudy days based on limited clear days’ Landsat ET fraction (ETf) computed by SSEBop. The Moderate Resolution Imaging Spectroradiometer (MODIS) remote sensing data can provide daily surface observation over clear-sky areas. This paper presented an enhanced gap-filling scheme for the SSEBop ET model, which improved the temporal resolution of Landsat ETf through the spatio-temporal fusion with SSEBop MODIS ETf on clear days and increased the time reconstruction accuracy of field-scale ET. The results were validated with the eddy covariance (EC) measurements over cropland in northwestern China. It indicated that the improved scheme performed better than the original SSEBop Landsat approach in daily ET estimation, with higher Nash-Sutcliffe efficiency (NSE, 0.75 vs. 0.70), lower root mean square error (RMSE, 0.95 mm·d-1 vs. 1.05 mm·d-1), and percent bias (PBias, 16.5% vs. 25.0%). This fusion method reduced the proportion of deviation (13.3% vs. 25.5%) in the total errors and made the random error the main proportion, which can be reduced over time and space in regional ET estimation. It also evidently improved the underestimation of crop ET by the SSEBop Landsat scheme during irrigation before sowing and could more accurately describe the synergistic changes of soil moisture and cropland ET. The proposed MODIS and Landsat ETf fusion can significantly improve the accuracy of SSEBop in estimating field-scale ET.
- 17 February 2022
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 17 (2) , e0264133
Open AccessOperational daily evapotranspiration mapping at field scale based on SSEBop model and spatiotemporal fusion of multi-source remote sensing data
Accurate understanding of daily evapotranspiration (ET) at field scale is of great significance for agricultural water resources management. The operational simplified surface energy balance (SSEBop) model has been applied to estimate field scale ET with Landsat satellite imagery. However, there is still uncertainty in the ET time reconstruction for cloudy days based on limited clear days’ Landsat ET fraction (ETf) computed by SSEBop. The Moderate Resolution Imaging Spectroradiometer (MODIS) remote sensing data can provide daily surface observation over clear-sky areas. This paper presented an enhanced gap-filling scheme for the SSEBop ET model, which improved the temporal resolution of Landsat ETf through the spatio-temporal fusion with SSEBop MODIS ETf on clear days and increased the time reconstruction accuracy of field-scale ET. The results were validated with the eddy covariance (EC) measurements over cropland in northwestern China. It indicated that the improved scheme performed better than the original SSEBop Landsat approach in daily ET estimation, with higher Nash-Sutcliffe efficiency (NSE, 0.75 vs. 0.70), lower root mean square error (RMSE, 0.95 mm·d-1 vs. 1.05 mm·d-1), and percent bias (PBias, 16.5% vs. 25.0%). This fusion method reduced the proportion of deviation (13.3% vs. 25.5%) in the total errors and made the random error the main proportion, which can be reduced over time and space in regional ET estimation. It also evidently improved the underestimation of crop ET by the SSEBop Landsat scheme during irrigation before sowing and could more accurately describe the synergistic changes of soil moisture and cropland ET. The proposed MODIS and Landsat ETf fusion can significantly improve the accuracy of SSEBop in estimating field-scale ET.