Real-Time Forecast of SMAP L3 Soil Moisture Using Spatial–Temporal Deep Learning Model with Data Integration
Soil moisture (SM) has significant impacts on the Earth’s energy and water cycle system. Remote sensing, such as the Soil Moisture Active Passive (SMAP) mission, has delivered valuable estimations of global surface soil moisture. However, it has a 2~3 days revisit time leading to gaps between SMAP a...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-01-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/15/2/366 |
_version_ | 1797437521844502528 |
---|---|
author | Ye Zhang Feini Huang Lu Li Qinglian Li Yongkun Zhang Wei Shangguan |
author_facet | Ye Zhang Feini Huang Lu Li Qinglian Li Yongkun Zhang Wei Shangguan |
author_sort | Ye Zhang |
collection | DOAJ |
description | Soil moisture (SM) has significant impacts on the Earth’s energy and water cycle system. Remote sensing, such as the Soil Moisture Active Passive (SMAP) mission, has delivered valuable estimations of global surface soil moisture. However, it has a 2~3 days revisit time leading to gaps between SMAP areas. To achieve accurate and comprehensive real-time forecast of SM, we propose a spatial–temporal deep learning model based on the Convolutional Gated Recursive Units with Data Integration (DI_ConvGRU) to capture the spatial and temporal variation in SM simultaneously by modeling the influence of adjacent SM values in space and time. Experiments show that the DI_ConvGRU outperforms the ConvGRU with Linear Interpolation (interp_ConvGRU) and the Long Short-Term Memory with Data Integration (DI_LSTM). The best performance (Bias = 0.0132 m<sup>3</sup>/m<sup>3</sup>, ubRMSE = 0.022 m<sup>3</sup>/m<sup>3</sup>, R = 0.977) has been achieved through the use of spatial–temporal deep learning model and Data Integration term. In comparison with interp_ConvGRU and DI_LSTM, DI_ConvGRU has improved the model performance in 74.88% and 68.99% of the regions according to RMSE, respectively. The predictability of SM depends highly on SM memory characteristics. DI_ConvGRU can provide accurate spatial–temporal forecast for SM with missing data, making them potentially useful for applications such as filling observational gaps in satellite data. |
first_indexed | 2024-03-09T11:20:33Z |
format | Article |
id | doaj.art-bf5a2f3fa71840a9aeb2f91999a7e170 |
institution | Directory Open Access Journal |
issn | 2072-4292 |
language | English |
last_indexed | 2024-03-09T11:20:33Z |
publishDate | 2023-01-01 |
publisher | MDPI AG |
record_format | Article |
series | Remote Sensing |
spelling | doaj.art-bf5a2f3fa71840a9aeb2f91999a7e1702023-12-01T00:19:36ZengMDPI AGRemote Sensing2072-42922023-01-0115236610.3390/rs15020366Real-Time Forecast of SMAP L3 Soil Moisture Using Spatial–Temporal Deep Learning Model with Data IntegrationYe Zhang0Feini Huang1Lu Li2Qinglian Li3Yongkun Zhang4Wei Shangguan5Southern Marine Science and Engineering Guangdong Laboratory (Zhuhai), Guangdong Province Key Laboratory for Climate Change and Natural Disaster Studies, School of Atmospheric Sciences, Sun Yat-Sen University, Guangzhou 510275, ChinaSouthern Marine Science and Engineering Guangdong Laboratory (Zhuhai), Guangdong Province Key Laboratory for Climate Change and Natural Disaster Studies, School of Atmospheric Sciences, Sun Yat-Sen University, Guangzhou 510275, ChinaSouthern Marine Science and Engineering Guangdong Laboratory (Zhuhai), Guangdong Province Key Laboratory for Climate Change and Natural Disaster Studies, School of Atmospheric Sciences, Sun Yat-Sen University, Guangzhou 510275, ChinaCollege of Computer Science and Technology, Changchun Normal University, Changchun 130032, ChinaSouthern Marine Science and Engineering Guangdong Laboratory (Zhuhai), Guangdong Province Key Laboratory for Climate Change and Natural Disaster Studies, School of Atmospheric Sciences, Sun Yat-Sen University, Guangzhou 510275, ChinaSouthern Marine Science and Engineering Guangdong Laboratory (Zhuhai), Guangdong Province Key Laboratory for Climate Change and Natural Disaster Studies, School of Atmospheric Sciences, Sun Yat-Sen University, Guangzhou 510275, ChinaSoil moisture (SM) has significant impacts on the Earth’s energy and water cycle system. Remote sensing, such as the Soil Moisture Active Passive (SMAP) mission, has delivered valuable estimations of global surface soil moisture. However, it has a 2~3 days revisit time leading to gaps between SMAP areas. To achieve accurate and comprehensive real-time forecast of SM, we propose a spatial–temporal deep learning model based on the Convolutional Gated Recursive Units with Data Integration (DI_ConvGRU) to capture the spatial and temporal variation in SM simultaneously by modeling the influence of adjacent SM values in space and time. Experiments show that the DI_ConvGRU outperforms the ConvGRU with Linear Interpolation (interp_ConvGRU) and the Long Short-Term Memory with Data Integration (DI_LSTM). The best performance (Bias = 0.0132 m<sup>3</sup>/m<sup>3</sup>, ubRMSE = 0.022 m<sup>3</sup>/m<sup>3</sup>, R = 0.977) has been achieved through the use of spatial–temporal deep learning model and Data Integration term. In comparison with interp_ConvGRU and DI_LSTM, DI_ConvGRU has improved the model performance in 74.88% and 68.99% of the regions according to RMSE, respectively. The predictability of SM depends highly on SM memory characteristics. DI_ConvGRU can provide accurate spatial–temporal forecast for SM with missing data, making them potentially useful for applications such as filling observational gaps in satellite data.https://www.mdpi.com/2072-4292/15/2/366soil moisturedeep learningforecasting techniquesSMAPremote sensing |
spellingShingle | Ye Zhang Feini Huang Lu Li Qinglian Li Yongkun Zhang Wei Shangguan Real-Time Forecast of SMAP L3 Soil Moisture Using Spatial–Temporal Deep Learning Model with Data Integration Remote Sensing soil moisture deep learning forecasting techniques SMAP remote sensing |
title | Real-Time Forecast of SMAP L3 Soil Moisture Using Spatial–Temporal Deep Learning Model with Data Integration |
title_full | Real-Time Forecast of SMAP L3 Soil Moisture Using Spatial–Temporal Deep Learning Model with Data Integration |
title_fullStr | Real-Time Forecast of SMAP L3 Soil Moisture Using Spatial–Temporal Deep Learning Model with Data Integration |
title_full_unstemmed | Real-Time Forecast of SMAP L3 Soil Moisture Using Spatial–Temporal Deep Learning Model with Data Integration |
title_short | Real-Time Forecast of SMAP L3 Soil Moisture Using Spatial–Temporal Deep Learning Model with Data Integration |
title_sort | real time forecast of smap l3 soil moisture using spatial temporal deep learning model with data integration |
topic | soil moisture deep learning forecasting techniques SMAP remote sensing |
url | https://www.mdpi.com/2072-4292/15/2/366 |
work_keys_str_mv | AT yezhang realtimeforecastofsmapl3soilmoistureusingspatialtemporaldeeplearningmodelwithdataintegration AT feinihuang realtimeforecastofsmapl3soilmoistureusingspatialtemporaldeeplearningmodelwithdataintegration AT luli realtimeforecastofsmapl3soilmoistureusingspatialtemporaldeeplearningmodelwithdataintegration AT qinglianli realtimeforecastofsmapl3soilmoistureusingspatialtemporaldeeplearningmodelwithdataintegration AT yongkunzhang realtimeforecastofsmapl3soilmoistureusingspatialtemporaldeeplearningmodelwithdataintegration AT weishangguan realtimeforecastofsmapl3soilmoistureusingspatialtemporaldeeplearningmodelwithdataintegration |