Soil Moisture Retrievals by Combining Passive Microwave and Optical Data
This paper aims to retrieve the temporal dynamics of soil moisture from 2015 to 2019 over an agricultural site in Southeast Australia using the Soil Moisture Active Passive (SMAP) brightness temperature. To meet this objective, two machine learning approaches, Random Forest (RF), Support Vector Mach...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-09-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/12/19/3173 |
id |
doaj-fd00e48d00044815844c97a81b8187da |
---|---|
record_format |
Article |
spelling |
doaj-fd00e48d00044815844c97a81b8187da2020-11-25T03:18:54ZengMDPI AGRemote Sensing2072-42922020-09-01123173317310.3390/rs12193173Soil Moisture Retrievals by Combining Passive Microwave and Optical DataCheng Tong0Hongquan Wang1Ramata Magagi2Kalifa Goïta3Luyao Zhu4Mengying Yang5Jinsong Deng6College of Environmental and Resource Sciences, Zhejiang University, Hangzhou 310029, ChinaCollege of Environmental and Resource Sciences, Zhejiang University, Hangzhou 310029, ChinaCentre d’Applications et de Recherche en Télédétection, Université de Sherbrooke, Sherbrooke, QC J1K 2R1, CanadaCentre d’Applications et de Recherche en Télédétection, Université de Sherbrooke, Sherbrooke, QC J1K 2R1, CanadaCollege of Environmental and Resource Sciences, Zhejiang University, Hangzhou 310029, ChinaCollege of Environmental and Resource Sciences, Zhejiang University, Hangzhou 310029, ChinaCollege of Environmental and Resource Sciences, Zhejiang University, Hangzhou 310029, ChinaThis paper aims to retrieve the temporal dynamics of soil moisture from 2015 to 2019 over an agricultural site in Southeast Australia using the Soil Moisture Active Passive (SMAP) brightness temperature. To meet this objective, two machine learning approaches, Random Forest (RF), Support Vector Machine (SVM), as well as a statistical Ordinary Least Squares (OLS) model were established, with the auxiliary data including the 16-day composite MODIS NDVI (MOD13Q1) and Surface Temperature (ST). The entire data were divided into two parts corresponding to ascending (6:00 p.m. local time) and descending (6:00 a.m. local time) orbits of SMAP overpasses. Thus, the three models were trained using the descending data acquired during the five years (2015 to 2019), and validated using the ascending product of the same period. Consequently, three different temporal variations of the soil moisture were obtained based on the three models. To evaluate their accuracies, the retrieved soil moisture was compared against the SMAP level-2 soil moisture product, as well as to in-situ ground station data. The comparative results show that the soil moisture obtained using the OLS, RF and SVM algorithms are highly correlated to the SMAP level-2 product, with high coefficients of determination (R<sup>2</sup><sub>OLS</sub> = 0.981, R<sup>2</sup><sub>SVM</sub> = 0.943, R<sup>2</sup><sub>RF</sub> = 0.983) and low RMSE (RMSE<sub>OLS</sub> = 0.016 cm<sup>3</sup>/cm<sup>3</sup>, RMSE<sub>SVM</sub> = 0.047 cm<sup>3</sup>/cm<sup>3</sup>, RMSE<sub>RF</sub> = 0.016 cm<sup>3</sup>/cm<sup>3</sup>). Meanwhile, the estimated soil moistures agree with in-situ station data across different years (R<sup>2</sup><sub>OLS</sub> = 0.376~0.85, R<sup>2</sup><sub>SVM</sub> = 0.376~0.814, R<sup>2</sup><sub>RF</sub> = 0.39~0.854; RMSE<sub>OLS</sub> = 0.049~0.105 cm<sup>3</sup>/cm<sup>3</sup>, RMSE<sub>SVM</sub> = 0.073~0.1 cm<sup>3</sup>/cm<sup>3</sup>, RMSE<sub>RF</sub> = 0.047~0.102 cm<sup>3</sup>/cm<sup>3</sup>), but an overestimation issue is observed for high vegetation conditions. The RF algorithm outperformed the SVM and OLS, in terms of the agreement with the ground measurements. This study suggests an alternative soil moisture retrieval scheme, in complementary to the SMAP baseline algorithm, for a fast soil moisture retrieval.https://www.mdpi.com/2072-4292/12/19/3173soil moistureSMAPrandom forestsupport vector machineordinary least square regression |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Cheng Tong Hongquan Wang Ramata Magagi Kalifa Goïta Luyao Zhu Mengying Yang Jinsong Deng |
spellingShingle |
Cheng Tong Hongquan Wang Ramata Magagi Kalifa Goïta Luyao Zhu Mengying Yang Jinsong Deng Soil Moisture Retrievals by Combining Passive Microwave and Optical Data Remote Sensing soil moisture SMAP random forest support vector machine ordinary least square regression |
author_facet |
Cheng Tong Hongquan Wang Ramata Magagi Kalifa Goïta Luyao Zhu Mengying Yang Jinsong Deng |
author_sort |
Cheng Tong |
title |
Soil Moisture Retrievals by Combining Passive Microwave and Optical Data |
title_short |
Soil Moisture Retrievals by Combining Passive Microwave and Optical Data |
title_full |
Soil Moisture Retrievals by Combining Passive Microwave and Optical Data |
title_fullStr |
Soil Moisture Retrievals by Combining Passive Microwave and Optical Data |
title_full_unstemmed |
Soil Moisture Retrievals by Combining Passive Microwave and Optical Data |
title_sort |
soil moisture retrievals by combining passive microwave and optical data |
publisher |
MDPI AG |
series |
Remote Sensing |
issn |
2072-4292 |
publishDate |
2020-09-01 |
description |
This paper aims to retrieve the temporal dynamics of soil moisture from 2015 to 2019 over an agricultural site in Southeast Australia using the Soil Moisture Active Passive (SMAP) brightness temperature. To meet this objective, two machine learning approaches, Random Forest (RF), Support Vector Machine (SVM), as well as a statistical Ordinary Least Squares (OLS) model were established, with the auxiliary data including the 16-day composite MODIS NDVI (MOD13Q1) and Surface Temperature (ST). The entire data were divided into two parts corresponding to ascending (6:00 p.m. local time) and descending (6:00 a.m. local time) orbits of SMAP overpasses. Thus, the three models were trained using the descending data acquired during the five years (2015 to 2019), and validated using the ascending product of the same period. Consequently, three different temporal variations of the soil moisture were obtained based on the three models. To evaluate their accuracies, the retrieved soil moisture was compared against the SMAP level-2 soil moisture product, as well as to in-situ ground station data. The comparative results show that the soil moisture obtained using the OLS, RF and SVM algorithms are highly correlated to the SMAP level-2 product, with high coefficients of determination (R<sup>2</sup><sub>OLS</sub> = 0.981, R<sup>2</sup><sub>SVM</sub> = 0.943, R<sup>2</sup><sub>RF</sub> = 0.983) and low RMSE (RMSE<sub>OLS</sub> = 0.016 cm<sup>3</sup>/cm<sup>3</sup>, RMSE<sub>SVM</sub> = 0.047 cm<sup>3</sup>/cm<sup>3</sup>, RMSE<sub>RF</sub> = 0.016 cm<sup>3</sup>/cm<sup>3</sup>). Meanwhile, the estimated soil moistures agree with in-situ station data across different years (R<sup>2</sup><sub>OLS</sub> = 0.376~0.85, R<sup>2</sup><sub>SVM</sub> = 0.376~0.814, R<sup>2</sup><sub>RF</sub> = 0.39~0.854; RMSE<sub>OLS</sub> = 0.049~0.105 cm<sup>3</sup>/cm<sup>3</sup>, RMSE<sub>SVM</sub> = 0.073~0.1 cm<sup>3</sup>/cm<sup>3</sup>, RMSE<sub>RF</sub> = 0.047~0.102 cm<sup>3</sup>/cm<sup>3</sup>), but an overestimation issue is observed for high vegetation conditions. The RF algorithm outperformed the SVM and OLS, in terms of the agreement with the ground measurements. This study suggests an alternative soil moisture retrieval scheme, in complementary to the SMAP baseline algorithm, for a fast soil moisture retrieval. |
topic |
soil moisture SMAP random forest support vector machine ordinary least square regression |
url |
https://www.mdpi.com/2072-4292/12/19/3173 |
work_keys_str_mv |
AT chengtong soilmoistureretrievalsbycombiningpassivemicrowaveandopticaldata AT hongquanwang soilmoistureretrievalsbycombiningpassivemicrowaveandopticaldata AT ramatamagagi soilmoistureretrievalsbycombiningpassivemicrowaveandopticaldata AT kalifagoita soilmoistureretrievalsbycombiningpassivemicrowaveandopticaldata AT luyaozhu soilmoistureretrievalsbycombiningpassivemicrowaveandopticaldata AT mengyingyang soilmoistureretrievalsbycombiningpassivemicrowaveandopticaldata AT jinsongdeng soilmoistureretrievalsbycombiningpassivemicrowaveandopticaldata |
_version_ |
1724625091417866240 |