Assessing the performance of satellite soil moisture on agricultural drought monitoring in the North China Plain

Cao, Meng; Chen, Min; Ji, Liu; Liu, Yanli

doi:10.1016/j.agwat.2021.107450

Cited by 29 publications

(26 citation statements)

References 77 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To mitigate the impact of bias, several studies advocate for applying a bias correction before calculating drought indicators. For SMAP, studies found that a bias correction against in situ or modeled data on the satellite SM data improved drought monitoring skill (Mishra et al, 2017;Cao et al, 2022). These results demonstrate that the accuracy of the satellite SM products is crucial for estimating drought duration and a scaling of SM to in situ SM or model SM data prior to calculation of a drought index is recommended.…”

Section: Plant Available Water Approachesmentioning

confidence: 86%

“…Anomalies and percentiles (Champagne et al, 2011;Nicolai-Shaw et al, 2017;van Hateren et al, 2021;Vroege et al, Soil Moisture Deficiency Index (SMDI) (Pablos et al, 2017;Xu et al, 2018;Fang et al, 2021) Soil Water Deficit Index (SWDI) (Martínez-Fernández et al, 2016Mishra et al, 2017;Pablos et al, 2017;Paredes-Trejo and Barbosa, 2017;Bai et al, 2018;Fang et al, 2021;Paredes-Trejo et al, 2021;Zhou et al, 2021;Cao et al, 2022;Chatterjee et al, 2022;Wu et al, 2022)…”

Section: Indicator Equation Common Thresholdsmentioning

confidence: 99%

“…This allows for the use of shorter satellite SM datasets such as NASAs SMAP (launched in 2015) and Sentinel-1 (launched in 2014). For example, the Soil Water Deficit Index (SWDI) (Martínez-Fernández et al, 2016;Mishra et al, 2017;Pablos et al, 2017;Paredes-Trejo and Barbosa, 2017;Bai et al, 2018;Zhu et al, 2019;Fang et al, 2021;Zhou et al, 2021;Cao et al, 2022) can be calculated as the SM scaled between field capacity and wilting point, indicating drought conditions when the value is below 0. The benefit of SWDI for short time series was demonstrated by Mishra et al (2017) who calculated SWDI over the continental US from SMAP passive microwave SM observations.…”

Section: Plant Available Water Approachesmentioning

confidence: 99%

See 2 more Smart Citations

Microwave remote sensing for agricultural drought monitoring: Recent developments and challenges

et al. 2022

View full text Add to dashboard Cite

Agricultural droughts are extreme events which are often a result of interplays between multiple hydro-meteorological processes. Therefore, assessing drought occurrence, extent, duration and intensity is complex and requires the combined use of multiple variables, such as temperature, rainfall, soil moisture (SM) and vegetation state. The benefit of using information on SM and vegetation state is that they integrate information on precipitation, temperature and evapotranspiration, making them direct indicators of plant available water and vegetation productivity. Microwave remote sensing enables the retrieval of both SM and vegetation information, and satellite-based SM and vegetation products are available operationally and free of charge on a regional or global scale and daily basis. As a result, microwave remote sensing products play an increasingly important role in drought monitoring applications. Here, we provide an overview of recent developments in using microwave remote sensing for large-scale agricultural drought monitoring. We focus on the intricacy of monitoring the complex process of drought development using multiple variables. First, we give a brief introduction on fundamental concepts of microwave remote sensing together with an overview of recent research, development and applications of drought indicators derived from microwave-based satellite SM and vegetation observations. This is followed by a more detailed overview of the current research gaps and challenges in combining microwave-based SM and vegetation measurements with hydro-meteorological data sets. The potential of using microwave remote sensing for drought monitoring is demonstrated through a case study over Senegal using multiple satellite- and model-based data sets on rainfall, SM, vegetation and combinations thereof. The case study demonstrates the added-value of microwave-based SM and vegetation observations for drought monitoring applications. Finally, we provide an outlook on potential developments and opportunities.

show abstract

Section: Plant Available Water Approachesmentioning

confidence: 86%

Section: Indicator Equation Common Thresholdsmentioning

confidence: 99%

Section: Plant Available Water Approachesmentioning

confidence: 99%

See 1 more Smart Citation

Microwave remote sensing for agricultural drought monitoring: Recent developments and challenges

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Spring agricultural drought is caused by low soil moisture (SM) that satisfies crop seedling emergence and growth requirements, which affects spring crop sowing and results in significant reductions in crop yield (Baik et al, 2019; Quiring & Papakryiakou, 2003). Therefore, accurate monitoring and forecasting of the spatiotemporal distribution of spring agricultural drought are essential for agricultural production (Cao et al, 2022). SM is the most direct variable for performing drought monitoring and has high spatial heterogeneity, which is influenced by multiple factors, such as meteorological conditions, vegetation cover, topography, and soil properties (Eswar et al, 2018; He et al, 2020; Y. Liu et al, 2020; Zhu et al, 2021).…”

Section: Introductionmentioning

confidence: 99%

Prediction of spring agricultural drought using machine learning algorithms in the southern Songnen Plain, China

Chen

Jiang³

et al. 2023

Land Degrad Dev

View full text Add to dashboard Cite

Winter climate conditions have a great effect on spring soil moisture (SM) in cold regions. The frequent occurrence of spring drought events in the Songnen Plain poses a significant threat to food security. In this study, we selected the random forest (RF) algorithm from three currently popular machine learning algorithms to predict the spatial pattern of average SM for the period of April 1–15 and April 16–30 with 1 km resolution in the dry cropland of southern Songnen Plain (SSNP) using 0–10 cm SM data for each April from 81 agro‐meteorological stations and winter climate data (e.g., temperature, snowfall), soil properties and topographic relief. Compared to the existing ERA5_Land and SMAP SM products, we obtain higher precision SM data (April 1–15: r = 0.74, RMSE = 0.050 m3 m−3; April 16–30: r = 0.73, RMSE = 0.051 m3 m−3). Drought grades were classified based on predicted SM data, and the results indicate agricultural drought was mainly influenced by the change of winter snowfall/snow depth, with western SSNP being more susceptible to drought because of soil properties. Compared with current SM data products, the RF model proposed in this study can implement more accurate prediction of spring soil drought based on winter climate, provide important information for agricultural management departments to prepare for spring cropping and irrigation, and avoid further soil salinization caused by drought.

show abstract

“…Soil moisture content (SMC) is a key variable affecting the water and energy balance in arid zones and the most important constraint in research on global and regional climate change, energy balance, and water cycle (Seneviratne et al, 2010). SMC directly affects crop growth and development and thus is an important factor in growth monitoring, yield prediction, and other agricultural applications (Ahmadi et al, 2022; Cao et al, 2022; Shaukat et al, 2022). Therefore, it is essential to collect high‐precision and large‐scale data on soil moisture for agricultural production purposes.…”

Section: Introductionmentioning

confidence: 99%

Remote sensing‐based retrieval of soil moisture content using stacking ensemble learning models

Wang

et al. 2022

Land Degrad Dev

View full text Add to dashboard Cite

Machine learning combined with multisource remote sensing data to assess soil moisture content (SMC) has attracted considerable attention in SMC studies, but the retrieval results still remain uncertain. The purpose of this study is to combine multiple single machine learning models with integrated learning algorithms and propose an SMC retrieval method based on multiple differentiated models under a stacking integrated learning architecture. First, 19 factors, including: radar backscattering coefficient, vegetation index, and drought index, that affect SMC were extracted from SENTINEL-1, LANDSAT, and terrain factors. Those with the highest importance scores were selected as retrieval factors using the Boruta algorithm combined with four single machine learning methods-classified regression tree, random forest, gradient boosting decision tree (GBDT), and extreme random tree. In addition, the two stacking ensemble models using least absolute shrinkage and selection operator (LASSO) and the generalized boosted regression model (GBM) were tested and applied to build the most reliable and accurate estimation model. The results showed that radar backscattering coefficient, temperature, vegetation drought index, land surface temperature, enhanced vegetation index, and solar local incident angle were the most important environmental variables for soil moisture retrieval. A comparison of the four machine learning methods in April and August showed that the GBDT model revealed the highest SMC retrieval accuracy, with root mean square error values of 1.87% and 1.64%, respectively. The stacking models were more accurate than the optimal single machine learning model, especially when using GBM. The multifactor integrated model constructed using spectral indices, radar backscatter coefficients, and topographic data exhibited high accuracy in soil surface moisture retrieval in an arid zone, providing a reference for land desertification studies and ecological environment management in the study region.

show abstract

Assessing the performance of satellite soil moisture on agricultural drought monitoring in the North China Plain

Cited by 29 publications

References 77 publications

Microwave remote sensing for agricultural drought monitoring: Recent developments and challenges

Microwave remote sensing for agricultural drought monitoring: Recent developments and challenges

Prediction of spring agricultural drought using machine learning algorithms in the southern Songnen Plain, China

Remote sensing‐based retrieval of soil moisture content using stacking ensemble learning models

Contact Info

Product

Resources

About