Downscaling SMAP Soil Moisture Retrievals Over an Agricultural Region in Central Mexico Using Machine Learning

Hernandez-Sanchez, Juan Carlos; Monsiváis-Huertero, Alejandro; Judge, Jasmeet; Jiménez-Escalona, José Carlos

doi:10.1109/igarss.2019.8900285

Cited by 3 publications

(4 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Classical ML offers accurate and computationally cheap techniques for SM downscaling. Hernández-Sánchez et al [62] used self-regularised regressive models in downscaling an SMAP 36 km SM product into 1 km by using high-spatial-resolution auxiliary information. Regularisation in ML is normally used to reduce the overfitting of the model.…”

Section: Classical-ml-model-based Downscaling Approachesmentioning

confidence: 99%

“…Modelbased methods involve approaches using statistical models, e.g., [52][53][54], LSMs, e.g., [55,56], and data assimilation techniques, e.g., [57,58]. Most downscaling techniques build a relationship between the high-resolution SM and the coarse-resolution SM using ancillary variables such as vegetation, land surface variables, soil characteristics, and climatic conditions [59][60][61][62][63][64]. This relationship often becomes non-linear and complex, in order to explain the processes underpinning SM variability in terms of key environmental variables.…”

Section: Introductionmentioning

confidence: 99%

“…Studies using more than one ML technique are comparatively discussed for their performance in downscaling. The paper further explores important insights gained from each study regarding surface ancillary variables Most downscaling techniques build a relationship between the high-resolution SM and the coarse-resolution SM using ancillary variables such as vegetation, land surface variables, soil characteristics, and climatic conditions [59][60][61][62][63][64]. This relationship often becomes non-linear and complex, in order to explain the processes underpinning SM variability in terms of key environmental variables.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Spatial Downscaling of Satellite-Based Soil Moisture Products Using Machine Learning Techniques: A Review

Senanayake,

Pathira Arachchilage,

Yeo

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

Soil moisture (SM) is a key variable driving hydrologic, climatic, and ecological processes. Although it is highly variable, both spatially and temporally, there is limited data availability to inform about SM conditions at adequate spatial and temporal scales over large regions. Satellite SM retrievals, especially L-band microwave remote sensing, has emerged as a feasible solution to offer spatially continuous global-scale SM information. However, the coarse spatial resolution of these L-band microwave SM retrievals poses uncertainties in many regional- and local-scale SM applications which require a high amount of spatial details. Numerous studies have been conducted to develop downscaling algorithms to enhance the spatial resolution of coarse-resolution satellite-derived SM datasets. Machine Learning (ML)-based downscaling models have gained prominence recently due to their ability to capture non-linear, complex relationships between SM and its driving factors, such as vegetation, surface temperature, topography, and climatic conditions. This review paper presents a comprehensive review of the ML-based approaches used in SM downscaling. The usage of classical, ensemble, neural nets, and deep learning methods to downscale SM products and the comparison of multiple algorithms are detailed in this paper. Insights into the significance of surface ancillary variables for model accuracy and the improvements made to ML-based SM downscaling approaches are also discussed. Overall, this paper provides useful insights for future studies on developing reliable, high-spatial-resolution SM datasets using ML-based algorithms.

show abstract

Section: Classical-ml-model-based Downscaling Approachesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Spatial Downscaling of Satellite-Based Soil Moisture Products Using Machine Learning Techniques: A Review

Senanayake,

Pathira Arachchilage,

Yeo

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Zhao et al (2018), Abbaszadeh et al (2019), Hu et al (2020), andLiu et al (2020) used a machine-learning method called Random Forest (RF) model for SM downscaling incorporating explanatory variables. Other machine-learning methods that are less commonly used for downscaling purposes include the following: support vector (SRRM) (Hernández-Sánchez et al, 2019), and gradient boosting decision tree (GBDT) (Liu et al, 2020;Wei et al, 2019). Few studies have combined machine-learning and geostatistical methods.…”

mentioning

confidence: 99%

A Remote Sensing Driven Soil Moisture Estimator: Uncertain Downscaling With Geostatistically Based Use of Ancillary Data

Karamouz

Alipour

Roohinia

et al. 2022

Water Resources Research

View full text Add to dashboard Cite

Climate change directly impacts climatic factors like temperature and precipitation, resulting in devastating natural disasters. Soil moisture (SM) (defined as the water contained in the unsaturated soil zone) is a long-term indicator when investigating climate change. It plays a crucial role in water, energy, and carbon flow between soil and the atmosphere (McColl et al., 2017). SM could also be a factor in predicting and monitoring floods and droughts (Hu et al., 2020). Thus it is essential to have SM at suitable spatial scales, potentially enhancing the representation of hydrological and weather prediction in evapotranspiration, runoff, and precipitation models (Alemohammad et al., 2018). SM is the most important indicator of a region's water availability and climate change impacts. This was realized in the 1960s when Palmer Drought Severity Index was developed primarily based on SM variations. Palmer (1965) and many other relevant works have continued on SM measures as a driving force in regional water resources planning. Its position has been realized as the key basic hydrogeological data especially with the recent advances in SM data collection instrumentations, SM networking such as what is implemented in Oklahoma (Mesonet), and satellite technology advancement (Karamouz et al., 2022;McPherson et al., 2007). Although many in situ SM networks are available online but the scarcity of SM data in many developing regions is a serious issue that prevents a full advantage of utilizing this vital data in water balance assessments. Having satellite SM data with finer than resolutions is a breakthrough to allow these regions to exercise the benefits of SM in drought and flood studies. Karamouz, Ebrahimi, and Ghomlaghi (2021), combined citizen science subjective SM and MODIS satellite Land surface temperature (LST) (500 km resolution) data to estimate SM data in a remote area in the central part of Iran. Wildfire is another side effect of climate change around the world that has its casual roots in the reduction of SM. SM influences vegetation growth conditions. Dry vegetation and its root increase the flammability of the vegetation/trees. However, owing to a lack of global observation-based SM data, previous studies have focused on case studies at local to regional scales. Benefitting from recent advances in the satellite-based derivation of surface SM, new studies have been performed, analyzing on the global scale the role of SM in the occurrence of large wildfires (Hou & Orth, 2020).Flood is one of the most catastrophic natural disasters in the United States, particularly in the Southeast, where hurricanes and tropical storms are most prevalent, causing billions of dollars in damage annually and significant

show abstract

A Novel Methodology for Modeling Ground Water Changes in Irrigation using Machine Learning Techniques

Sarakutty

Kavitha

Hanumanthappa

2020

2020 2nd International Conference on Innovative Mechanisms for Industry Applications (ICIMIA)

View full text Add to dashboard Cite

Downscaling SMAP Soil Moisture Retrievals Over an Agricultural Region in Central Mexico Using Machine Learning

Cited by 3 publications

References 6 publications

Spatial Downscaling of Satellite-Based Soil Moisture Products Using Machine Learning Techniques: A Review

Spatial Downscaling of Satellite-Based Soil Moisture Products Using Machine Learning Techniques: A Review

A Remote Sensing Driven Soil Moisture Estimator: Uncertain Downscaling With Geostatistically Based Use of Ancillary Data

A Novel Methodology for Modeling Ground Water Changes in Irrigation using Machine Learning Techniques

Contact Info

Product

Resources

About