Remote Sensing of Surface Soil Moisture from FengYun MicroWave Radiation Imager (MWRI) Data Using a Machine Learning Technique

2020 ◽  
Author(s):  
Sibo Zhang ◽  
Wei Yao
Keyword(s):  
Machine Learning ◽  
Soil Moisture ◽  
Tibetan Plateau ◽  
Microwave Radiation ◽  
Missing Values ◽  
Surface Soil ◽  
Low Frequency ◽  
Global Scale ◽  
Western China ◽  
Surface Soil Moisture

<p>In the past, soil moisture can be retrieved from microwave imager over most of land conditions. However, the algorithm performances over Tibetan Plateau and the Northwest China vary greatly from one to another due to frozen soils and surface volumetric scattering. The majority of western Chinese region is often filled with invalid retrievals. In this study, Soil Moisture Operational Products System (SMOPS) products from NOAA are used as the learning objectives to train a  machine learning (random forest) model for FY-3C microwave radiation imager (MWRI) data with multivariable inputs: brightness temperatures from all 10 MWRI channels from 10 to 89 GHz, brightness temperature polarization ratios at 10.65, 18.7 and 23.8 GHz, height in DEM (digital elevation model) and statistical soil porosity map data. Since the vegetation penetration of MWRI observations is limited, we exclude forest, urban and snow/ice surfaces in this work. It is shown that our new method performs very well and derives the surface soil moisture over Tibetan Plateau without major missing values. Comparing to other soil moisture data, the volumetric soil moisture (VSM) from this study correlates with SMOPS products much better than the MWRI operational L2 VSM products. R<sup>2</sup> score increases from 0.3 to 0.6 and ubRMSE score improves significantly from 0.11 m<sup>3</sup> m<sup>-3</sup> to 0.04 m<sup>3</sup> m<sup>-3</sup> during the time period from 1 August 2017 to 31 May 2019. The spatial distribution of our MWRI VSM estimates is also much improved in western China. Moreover, our MWRI VSM estimates are in good agreement with the top 7 cm soil moisture of ECMWF ERA5 reanalysis data: R<sup>2</sup> = 0.62, ubRMSD = 0.114 m<sup>3</sup> m<sup>-3</sup> and mean bias = -0.014 m<sup>3</sup> m<sup>-3</sup> for a global scale. We note that there is a risk of data gap of AMSR2 from the present to 2025. Obviously, for satellite low frequency microwave observations, MWRI observations from FY-3 series satellites can be a benefit supplement to keep the data integrity and increase the data density, since FY-3B\-3C\-3D satellites launched in November 2010\September 2013\November 2017 are still working today, and FY-3D is designed to work until November 2022.</p>

scholarly journals Machine Learning to Estimate Surface Soil Moisture from Remote Sensing Data

Water ◽  
2020 ◽  
Vol 12 (11) ◽  
pp. 3223
Author(s):  
Hamed Adab ◽  
Renato Morbidelli ◽  
Carla Saltalippi ◽  
Mahmoud Moradian ◽  
Gholam Abbas Fallah Ghalhari
Keyword(s):  
Machine Learning ◽  
Remote Sensing ◽  
Soil Moisture ◽  
Surface Soil ◽  
Remote Sensing Data ◽  
Surface Soil Moisture ◽  
Machine Learning Methods ◽  
Land Use Types ◽  
Semi Arid Region ◽  
Semi Arid

Soil moisture is an integral quantity parameter in hydrology and agriculture practices. Satellite remote sensing has been widely applied to estimate surface soil moisture. However, it is still a challenge to retrieve surface soil moisture content (SMC) data in the heterogeneous catchment at high spatial resolution. Therefore, it is necessary to improve the retrieval of SMC from remote sensing data, which is important in the planning and efficient use of land resources. Many methods based on satellite-derived vegetation indices have already been developed to estimate SMC in various climatic and geographic conditions. Soil moisture retrievals were performed using statistical and machine learning methods as well as physical modeling techniques. In this study, an important experiment of soil moisture retrieval for investigating the capability of the machine learning methods was conducted in the early spring season in a semi-arid region of Iran. We applied random forest (RF), support vector machine (SVM), artificial neural network (ANN), and elastic net regression (EN) algorithms to soil moisture retrieval by optical and thermal sensors of Landsat 8 and knowledge of land-use types on previously untested conditions in a semi-arid region of Iran. The statistical comparisons show that RF method provided the highest Nash–Sutcliffe efficiency value (0.73) for soil moisture retrieval covered by the different land-use types. Combinations of surface reflectance and auxiliary geospatial data can provide more valuable information for SMC estimation, which shows promise for precision agriculture applications.

Exploring the use of machine-learning techniques to integrate ground- and remote sensing-based observations for efficient near-surface soil moisture mapping

2020 ◽  
Author(s):  
Sarah Schönbrodt-Stitt ◽  
Paolo Nasta ◽  
Nima Ahmadian ◽  
Markus Kurtenbach ◽  
Christopher Conrad ◽  
...  
Keyword(s):  
Machine Learning ◽  
Soil Moisture ◽  
Spatial Resolution ◽  
Surface Soil ◽  
Bare Soil ◽  
Small Scale ◽  
Surface Soil Moisture ◽  
Near Surface ◽  
Campania Region

<p>Mapping near-surface soil moisture (<em>θ</em>) is of tremendous relevance for a broad range of environment-related disciplines and meteorological, ecological, hydrological and agricultural applications. Globally available products offer the opportunity to address <em>θ</em> in large-scale modelling with coarse spatial resolution such as at the landscape level. However, <em>θ</em> estimation at higher spatial resolution is of vital importance for many small-scale applications. Therefore, we focus our study on a small-scale catchment (MFC2) belonging to the “Alento” hydrological observatory, located in southern Italy (Campania Region). The goal of this study is to develop new machine-learning approaches to estimate high grid-resolution (about 17 m cell size) <em>θ</em> maps from mainly backscatter measurements retrieved from C-band Synthetic Aperture Radar (SAR) based on Sentinel-1 (S1) images and from gridded terrain attributes. Thus, a workflow comprising a total of 48 SAR-based <em>θ</em> patterns estimated for 24 satellite overpass dates (revisit time of 6 days) each with ascendant and descendent orbits will be presented. To enable for the mapping, SAR-based <em>θ</em> data was calibrated with in-situ measurements carried out with a portable device during eight measurement campaigns at time of satellite overpasses (four overpass days in total with each ascendant and descendent satellite overpasses per day in November 2018). After the calibration procedure, data validation was executed from November 10, 2018 till March 28, 2019 by using two stationary sensors monitoring <em>θ</em> at high-temporal (1-min recording time). The specific sensor locations reflected two contrasting field conditions, one bare soil plot (frequently kept clear, without disturbance of vegetation cover) and one non-bare soil plot (real-world condition). Point-scale ground observations of <em>θ</em> were compared to pixel-scale (17 m × 17 m), SAR-based <em>θ</em> estimated for those pixels corresponding to the specific positions of the stationary sensors. Mapping performance was estimated through the root mean squared error (RMSE). For a short-term time series of <em>θ</em> (Nov 2018) integrating 136 in situ, sensor-based <em>θ</em> (<em>θ</em><sub>insitu</sub>) and 74 gravimetric-based <em>θ</em> (<em>θ</em><sub>gravimetric</sub>) measurements during a total of eight S1 overpasses, mapping performance already proved to be satisfactory with RMSE=0.039 m³m<sup>-</sup>³ and R²=0.92, respectively with RMSE=0.041 m³m<sup>-</sup>³ and R²=0.91. First results further reveal that estimated satellite-based <em>θ</em> patterns respond to the evolution of rainfall. With our workflow developed and results, we intend to contribute to improved environmental risk assessment by assimilating the results into hydrological models (e.g., HydroGeoSphere), and to support future studies on combined ground-based and SAR-based <em>θ</em> retrieval for forested land (future missions operating at larger wavelengths e.g. NISARL-band, Biomass P-band sensors).</p>

scholarly journals Effects of Patchiness on Surface Soil Moisture of Alpine Meadow on the Northeastern Qinghai-Tibetan Plateau: Implications for Grassland Restoration

2020 ◽  
Vol 12 (24) ◽  
pp. 4121
Author(s):  
Wei Zhang ◽  
Shuhua Yi ◽  
Yu Qin ◽  
Yi Sun ◽  
Donghui Shangguan ◽  
...  
Keyword(s):  
Soil Moisture ◽  
Tibetan Plateau ◽  
Surface Soil ◽  
Alpine Meadow ◽  
Alpine Grassland ◽  
Grassland Restoration ◽  
Landscape Indices ◽  
Surface Soil Moisture ◽  
Bare Patch

Surface soil moisture (SSM) is a key limiting factor for vegetation growth in alpine meadow on the Qinghai-Tibetan Plateau (QTP). Patches with various sizes and types may cause the redistribution of SSM by changing soil hydrological processes, and then trigger or accelerate alpine grassland degradation. Therefore, it is vital to understand the effects of patchiness on SSM at multi-scales to provide a reference for alpine grassland restoration. However, there is a lack of direct observational evidence concerning the role of the size and type of patches on SSM, and little is known about the effects of patches pattern on SSM at plot scale. Here, we first measured SSM of typical patches with different sizes and types at patch scale and investigated their patterns and SSM spatial distribution through unmanned aerial vehicle (UAV)-mounted multi-type cameras at plot scale. We then analyzed the role of the size and type of patchiness on SSM at both patch and plot scales. Results showed that: (1) in situ measured SSM of typical patches was significantly different (P < 0.01), original vegetation patch (OV) had the highest SSM, followed by isolate vegetation patch (IV), small bare patch (SP), medium bare patch (MP) and large bare patch (LP); (2) the proposed method based on UAV images was able to estimate SSM (0–40 cm) with a satisfactory accuracy (R2 = 0.89, P < 0.001); (3) all landscape indices of OV, with the exception of patch density, were positively correlated with SSM at plot scale, while most of the landscape indices of LP and IV showed negative correlations (P < 0.05). Our results indicated that patchiness intensified the spatial heterogeneity of SSM and potentially accelerated the alpine meadow degradation. Preventing the development of OV into IV and the expansion of LP is a critical task for alpine meadow management and restoration.

scholarly journals Monitoring Surface Soil Moisture Content over the Vegetated Area by Integrating Optical and SAR Satellite Observations in the Permafrost Region of Tibetan Plateau

2020 ◽  
Vol 12 (1) ◽  
pp. 183 ◽  
Author(s):  
Chenyang Xu ◽  
John J. Qu ◽  
Xianjun Hao ◽  
Di Wu
Keyword(s):  
Soil Moisture ◽  
Tibetan Plateau ◽  
Water Content ◽  
Vegetation Index ◽  
Surface Soil ◽  
Cloud Model ◽  
Incidence Angle ◽  
Permafrost Region ◽  
Surface Soil Moisture ◽  
The Impact

Surface soil moisture (SSM), the average water content of surface soil (up to 5 cm depth), plays a key role in the energy exchange within the ecosystem. We estimated SSM in areas with vegetation cover (grassland) by combining microwave and optical satellite measurements in the central Tibetan Plateau (TP) in 2015. We exploited TERRA moderate resolution imaging spectroradiometer (MODIS) and Sentinel-1A synthetic aperture radar (SAR) observations to estimate SSM through a simplified water-cloud model (sWCM). This model considers the impact of vegetation water content (VWC) to SSM retrieval by integrating the vegetation index (VI), the normalized difference water index (NDWI), or the normalized difference infrared index (NDII). Sentinel-1 SAR C-band backscattering coefficients, incidence angle, and NDWI/NDII were assimilated in the sWCM to monitor SSM. The soil moisture and temperature monitoring network on the central TP (CTP-SMTMN) measures SSM within the study area, and ground measurements were applied to train and validate the model. Via the proposed methods, we estimated the SSM in vegetated area with an R2 of 0.43 and a ubRMSE of 0.06 m3/m3 when integrating the NDWI and with an R2 of 0.45 and a ubRMSE of 0.06 m3/m3 when integrating the NDII.

Developing machine learning models with multisource inputs for improved land surface soil moisture in China

2022 ◽  
Vol 192 ◽  
pp. 106623
Author(s):  
Lei Wang ◽  
Shibo Fang ◽  
Zhifang Pei ◽  
Dong Wu ◽  
Yongchao Zhu ◽  
...  
Keyword(s):  
Machine Learning ◽  
Soil Moisture ◽  
Land Surface ◽  
Surface Soil ◽  
Learning Models ◽  
Surface Soil Moisture ◽  
Machine Learning Models

scholarly journals A Machine Learning-Based Approach for Surface Soil Moisture Estimations with Google Earth Engine

2021 ◽  
Vol 13 (11) ◽  
pp. 2099
Author(s):  
Felix Greifeneder ◽  
Claudia Notarnicola ◽  
Wolfgang Wagner
Keyword(s):  
Machine Learning ◽  
Soil Moisture ◽  
Moisture Content ◽  
Spatial Resolution ◽  
Soil Moisture Content ◽  
Surface Soil ◽  
High Spatial Resolution ◽  
Google Earth ◽  
Surface Soil Moisture ◽  
Google Earth Engine

Due to its relation to the Earth’s climate and weather and phenomena like drought, flooding, or landslides, knowledge of the soil moisture content is valuable to many scientific and professional users. Remote-sensing offers the unique possibility for continuous measurements of this variable. Especially for agriculture, there is a strong demand for high spatial resolution mapping. However, operationally available soil moisture products exist with medium to coarse spatial resolution only (≥1 km). This study introduces a machine learning (ML)—based approach for the high spatial resolution (50 m) mapping of soil moisture based on the integration of Landsat-8 optical and thermal images, Copernicus Sentinel-1 C-Band SAR images, and modelled data, executable in the Google Earth Engine. The novelty of this approach lies in applying an entirely data-driven ML concept for global estimation of the surface soil moisture content. Globally distributed in situ data from the International Soil Moisture Network acted as an input for model training. Based on the independent validation dataset, the resulting overall estimation accuracy, in terms of Root-Mean-Squared-Error and R², was 0.04 m3·m−3 and 0.81, respectively. Beyond the retrieval model itself, this article introduces a framework for collecting training data and a stand-alone Python package for soil moisture mapping. The Google Earth Engine Python API facilitates the execution of data collection and retrieval which is entirely cloud-based. For soil moisture retrieval, it eliminates the requirement to download or preprocess any input datasets.

scholarly journals Assimilation of space-based passive microwave soil moisture retrievals and the correction for a dynamic open water fraction

2012 ◽  
Vol 9 (1) ◽  
pp. 1013-1039 ◽  
Author(s):  
B. T. Gouweleeuw ◽  
A. I. J. M. van Dijk ◽  
J. P. Guerschman ◽  
P. Dyce ◽  
R. A. M. de Jeu ◽  
...  
Keyword(s):  
Soil Moisture ◽  
Surface Soil ◽  
Low Frequency ◽  
Open Water ◽  
Water Bodies ◽  
Surface Soil Moisture ◽  
Near Surface ◽  
Small Areas ◽  
Water Fraction ◽  
Moderate Resolution Imaging Spectroradiometer

Abstract. The large observation footprint of low-frequency satellite microwave emissions complicates the interpretation of near-surface soil moisture retrievals. While the effect of sub-footprint lateral heterogeneity is relatively limited under unsaturated conditions, open water bodies, if not accounted for, cause a strong positive bias in the satellite-derived soil moisture retrieval. This bias is generally assumed static and associated with large, continental lakes and coastal areas. Temporal changes in the extent of smaller water bodies as small as a few percent of the sensor footprint size, however, can cause significant and dynamic biases. We analysed the influence of such small open water bodies near-surface soil moisture retrieval data from the Advanced Microwave Scanning Radiometer for the Earth Observing System (AMSR-E) for three areas in Oklahoma, USA. Differences between on-ground observations, model estimates and AMSR-E retrievals were compared to dynamic estimates of open water fraction, one retrieved from a global daily record based on higher frequency AMSR-E data and another derived from the Moderate Resolution Imaging Spectroradiometer (MODIS). The comparisons demonstrates that seasonally varying biases of up to 30 vol.% soil water content can be attributed to the presence of relatively small areas (<5%) of open water in or near the sensor footprint. These errors need to be addressed, either through elimination or accurate characterization, if the soil moisture retrievals are to be used effectively in a data assimilation scheme.

scholarly journals Advances in soil moisture retrieval from multispectral remote sensing using unoccupied aircraft systems and machine learning techniques

2021 ◽  
Vol 25 (5) ◽  
pp. 2739-2758
Author(s):  
Samuel N. Araya ◽  
Anna Fryjoff-Hung ◽  
Andreas Anderson ◽  
Joshua H. Viers ◽  
Teamrat A. Ghezzehei
Keyword(s):  
Machine Learning ◽  
Remote Sensing ◽  
Soil Moisture ◽  
Surface Soil ◽  
Potential Evapotranspiration ◽  
Learning Algorithms ◽  
Variable Importance ◽  
Machine Learning Algorithms ◽  
Surface Soil Moisture ◽  
Multispectral Remote Sensing

Abstract. This study investigates the ability of machine learning models to retrieve the surface soil moisture of a grassland area from multispectral remote sensing carried out using an unoccupied aircraft system (UAS). In addition to multispectral images, we use terrain attributes derived from a digital elevation model and hydrological variables of precipitation and potential evapotranspiration as covariates to predict surface soil moisture. We tested four different machine learning algorithms and interrogated the models to rank the importance of different variables and to understand their relationship with surface soil moisture. All the machine learning algorithms we tested were able to predict soil moisture with good accuracy. The boosted regression tree algorithm was marginally the best, with a mean absolute error of 3.8 % volumetric moisture content. Variable importance analysis revealed that the four most important variables were precipitation, reflectance in the red wavelengths, potential evapotranspiration, and topographic position indices (TPI). Our results demonstrate that the dynamics of soil water status across heterogeneous terrain may be adequately described and predicted by UAS remote sensing and machine learning. Our modeling approach and the variable importance and relationships we have assessed in this study should be useful for management and environmental modeling tasks where spatially explicit soil moisture information is important.

Sign in / Sign up

Export Citation Format

Share Document