Leveraging the Google Earth Engine for Drought Assessment Using Global Soil Moisture Data

Sazib, Nazmus; Mladenova, I. E.; Bolten, J. D.

doi:10.3390/rs10081265

Cited by 124 publications

(73 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The GEE greatly improves the processing efficiency when using substantial amounts of remote sensing data. In recent years, the GEE was used in land cover mapping [49][50][51][52][53][54][55][56][57][58], agricultural applications [59][60][61][62][63], disaster management, and earth sciences studies [64][65][66]. This remote sensing data processing cloud platform makes the rapid processing of Sentinel-2 images covering large areas possible.…”

mentioning

confidence: 99%

Estimating Forest Stock Volume in Hunan Province, China, by Integrating In Situ Plot Data, Sentinel-2 Images, and Linear and Machine Learning Regression Models

Yang

et al. 2020

Remote Sensing

View full text Add to dashboard Cite

The forest stock volume (FSV) is one of the key indicators in forestry resource assessments on local, regional, and national scales. To date, scaling up in situ plot-scale measurements across landscapes is still a great challenge in the estimation of FSVs. In this study, Sentinel-2 imagery, the Google Earth Engine (GEE) cloud computing platform, three base station joint differential positioning technology (TBSJDPT), and three algorithms were used to build an FSV model for forests located in Hunan Province, southern China. The GEE cloud computing platform was used to extract the imagery variables from the Sentinel-2 imagery pixels. The TBSJDPT was put forward and used to provide high-precision positions of the sample plot data. The random forests (RF), support vector regression (SVR), and multiple linear regression (MLR) algorithms were used to estimate the FSV. For each pixel, 24 variables were extracted from the Sentinel-2 images taken in 2017 and 2018. The RF model performed the best in both the training phase (i.e., R 2 = 0.91, RMSE = 35.13 m 3 ha −1 , n = 321) and in the test phase (i.e., R 2 = 0.58, RMSE = 65.03 m 3 ha −1 , and n = 138). This model was followed by the SVR model (R 2 = 0.54, RMSE = 65.60 m 3 ha −1 , n = 321 in training; R 2 = 0.54, RMSE = 66.00 m 3 ha −1 , n = 138 in testing), which was slightly better than the MLR model (R 2 = 0.38, RMSE = 75.74 m 3 ha −1 , and n = 321 in training; R 2 = 0.49, RMSE = 70.22 m 3 ha −1 , and n = 138 in testing) in both the training phase and test phase. The best predictive band was Red-Edge 1 (B5), which performed well both in the machine learning methods and in the MLR method. The Blue band (B2), Green band (B3), Red band (B4), SWIR2 band (B12), and vegetation indices (TCW, NDVI_B5, and TCB) were used in the machine learning models, and only one vegetation index (MSI) was used in the MLR model. We mapped the FSV distribution in Hunan Province (3.50 × 10 8 m 3 ) based on the RF model; it reached a total accuracy of 63.87% compared with the official forest report in 2017 (5.48 × 10 8 m 3 ). The results from this study will help develop and improve satellite-based methods to estimate FSVs on local, regional and national scales.The forest stock volume (FSV, m 3 ha −1 ) is the sum of the stem volumes of all the living trees per unit area, and is one of key forest variables for forest resources management and assessments on local, region and country scales [1]. FSVs have a strong relationship with the aboveground biomass (AGB) and carbon stocks [2]. To understand the spatial distribution of carbon in forests and to derive predictions for monitoring carbon stock trends, the FSV must be quantified [3]. Traditionally, the FSV is estimated by sampling several plots, which involves substantial manpower, materials, and financial resources [4]. With the development of remote sensing technology, particularly the Landsat series since 1972, satellite imagery has played an important role in forest inventory. Various studies have been performed to estimate the forest variables ...

show abstract

mentioning

confidence: 99%

Estimating Forest Stock Volume in Hunan Province, China, by Integrating In Situ Plot Data, Sentinel-2 Images, and Linear and Machine Learning Regression Models

Yang

et al. 2020

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…These datasets are generated by integrating airborneor satellite-based soil moisture observations into a hydrologic model, which enhances the model performance and corrects for precipitation related inaccuracies [26]. Examples of such data sets are the SMAP L4 Root-zone soil moisture and the NASA-USDA Global Soil Moisture Data [26,79,105]. The latter is operationally used by the U.S. Department of Agriculture-Foreign Agricultural Service (USDA-FAS) for assessing the impact of drought on crop production (Figs.…”

Section: Observable: Soil Moisturementioning

confidence: 99%

Earth Observations and Integrative Models in Support of Food and Water Security

Ruane

Duncan

et al. 2019

Remote Sens Earth Syst Sci

View full text Add to dashboard Cite

Global food production depends upon many factors that Earth observing satellites routinely measure about water, energy, weather, and ecosystems. Increasingly sophisticated, publicly available satellite data products can improve efficiencies in resource management and provide earlier indication of environmental disruption. Satellite remote sensing provides a consistent, long-term record that can be used effectively to detect large-scale features over time, such as a developing drought. Accuracy and capabilities have increased along with the range of Earth observations and derived products that can support food security decisions with actionable information. This paper highlights major capabilities facilitated by satellite observations and physical models that have been developed and validated using remotely sensed observations. Although we primarily focus on variables relevant to agriculture, we also include a brief description of the growing use of Earth observations in support of aquaculture and fisheries.

show abstract

“…Phenology-based threshold methods have increasingly gained public and scientific attention in geospatial science. The Phenology-based classification has shown a promising level of accuracy for mapping vegetation, crops, and land cover using moderate to high spatial resolution satellite data [24,27,[54][55][56] with aid of GEE cloud computing technology [23,53,[57][58][59][60][61]. There has been some research effort to study surface phenology of vegetation, rubber plantation, and cropland mapping in tropical regions [62][63][64].…”

Section: Introductionmentioning

confidence: 99%

Determination of Vegetation Thresholds for Assessing Land Use and Land Use Changes in Cambodia using the Google Earth Engine Cloud-Computing Platform

et al. 2019

View full text Add to dashboard Cite

As more data and technologies become available, it is important that a simple method is developed for the assessment of land use changes because of the global need to understand the potential climate mitigation that could result from a reduction in deforestation and forest degradation in the tropics. Here, we determined the threshold values of vegetation types to classify land use categories in Cambodia through the analysis of phenological behaviors and the development of a robust phenology-based threshold classification (PBTC) method for the mapping and long-term monitoring of land cover changes. We accessed 2199 Landsat collections using Google Earth Engine (GEE) and applied the Enhanced Vegetation Index (EVI) and harmonic regression methods to identify phenological behaviors of land cover categories during the leaf-shedding phenology (LSP) and leaf-flushing phenology (LFS) seasons. We then generated 722 mean phenology EVI profiles for 12 major land cover categories and determined the threshold values for selected land cover categories in the mid-LSP season. The PBTC pixel-based classified map was validated using very high-resolution (VHR) imagery. We obtained a cumulative overall accuracy of more than 88% and a cumulative overall accuracy of the referenced forest cover of almost 85%. These high accuracy values suggest that the very first PBTC map can be useful for estimating the activity data, which are critically needed to assess land use changes and related carbon emissions under the Reducing Emissions from Deforestation and forest Degradation (REDD+) scheme. We found that GEE cloud-computing is an appropriate tool to use to access remote sensing big data at scale and at no cost.

show abstract

Leveraging the Google Earth Engine for Drought Assessment Using Global Soil Moisture Data

Cited by 124 publications

References 52 publications

Estimating Forest Stock Volume in Hunan Province, China, by Integrating In Situ Plot Data, Sentinel-2 Images, and Linear and Machine Learning Regression Models

Estimating Forest Stock Volume in Hunan Province, China, by Integrating In Situ Plot Data, Sentinel-2 Images, and Linear and Machine Learning Regression Models

Earth Observations and Integrative Models in Support of Food and Water Security

Determination of Vegetation Thresholds for Assessing Land Use and Land Use Changes in Cambodia using the Google Earth Engine Cloud-Computing Platform

Contact Info

Product

Resources

About