scholarly journals Random Forests with Bagging and Genetic Algorithms Coupled with Least Trimmed Squares Regression for Soil Moisture Deficit Using SMOS Satellite Soil Moisture

2021 ◽  
Vol 10 (8) ◽  
pp. 507
Author(s):  
Prashant K. Srivastava ◽  
George P. Petropoulos ◽  
Rajendra Prasad ◽  
Dimitris Triantakonstantis

Soil Moisture Deficit (SMD) is a key indicator of soil water content changes and is valuable to a variety of applications, such as weather and climate, natural disasters, agricultural water management, etc. Soil Moisture and Ocean Salinity (SMOS) is a dedicated mission focused on soil moisture retrieval and can be utilized for SMD estimation. In this study, the use of soil moisture derived from SMOS has been provided for the estimation of SMD at a catchment scale. Several approaches for the estimation of SMD are implemented herein, using algorithms such as Random Forests (RF) and Genetic Algorithms coupled with Least Trimmed Squares (GALTS) regression. The results show that for SMD estimation, the RF algorithm performed best as compared to the GALTS, with Root Mean Square Errors (RMSEs) of 0.021 and 0.024, respectively. All in all, our study findings can provide important assistance towards developing the accuracy and applicability of remote sensing-based products for operational use.

2020 ◽  
Vol 10 (10) ◽  
Author(s):  
M. Afzal ◽  
R. Ragab

Abstract In this study, the Distributed Catchment-Scale Model, DiCaSM, was used to study the impact of climate change on the hydrology of the Eden catchment, north east of Scotland. As a first step, the model was successfully calibrated and validated for a 42 years period. The DiCaSM model was then used to study the impact of climate change on the water availability. Data from the UKCP09 Climate change scenarios for the 2010–2039, 2040–2069 and 2070–2099 periods, considering three gas emission scenarios (low, medium and high), were applied. The results indicated that the greatest decrease in streamflow and groundwater recharge was projected to happen under the high emission scenarios towards the end of the century, i.e. between 2070 and 2099. This would mainly be due to the summers becoming drier. Meanwhile, the projected increase in winter precipitation did not contribute much towards groundwater recharge due the projected increases in evapotranspiration and soil moisture deficit. The following drought indices were calculated and were found to be effective in predicting different types of droughts: the Standardized Precipitation Index, SPI, and the Standardized Precipitation Evaporation Index, SPEI, the Reconnaissance Drought Index, RDI, the modified adjusted RDI, the Soil Moisture Deficit, SMD and the Wetness Index, WI. The findings of the study have broader implications in water resources management considering the future changes in climate.


Crop Science ◽  
1987 ◽  
Vol 27 (6) ◽  
pp. 1177-1184 ◽  
Author(s):  
R. B. Flagler ◽  
R. P. Patterson ◽  
A. S. Heagle ◽  
W. W. Heck

Forests ◽  
2015 ◽  
Vol 6 (12) ◽  
pp. 3748-3762 ◽  
Author(s):  
Ming-Han Yu ◽  
Guo-Dong Ding ◽  
Guang-Lei Gao ◽  
Yuan-Yuan Zhao ◽  
Lei Yan ◽  
...  

Science ◽  
2020 ◽  
Vol 370 (6520) ◽  
pp. 1095-1099 ◽  
Author(s):  
Peng Zhang ◽  
Jee-Hoon Jeong ◽  
Jin-Ho Yoon ◽  
Hyungjun Kim ◽  
S.-Y. Simon Wang ◽  
...  

Unprecedented heatwave-drought concurrences in the past two decades have been reported over inner East Asia. Tree-ring–based reconstructions of heatwaves and soil moisture for the past 260 years reveal an abrupt shift to hotter and drier climate over this region. Enhanced land-atmosphere coupling, associated with persistent soil moisture deficit, appears to intensify surface warming and anticyclonic circulation anomalies, fueling heatwaves that exacerbate soil drying. Our analysis demonstrates that the magnitude of the warm and dry anomalies compounding in the recent two decades is unprecedented over the quarter of a millennium, and this trend clearly exceeds the natural variability range. The “hockey stick”–like change warns that the warming and drying concurrence is potentially irreversible beyond a tipping point in the East Asian climate system.


2015 ◽  
Vol 54 (2) ◽  
pp. 126-131 ◽  
Author(s):  
Rogier P.O. Schulte ◽  
Iolanda Simo ◽  
Rachel E. Creamer ◽  
Nicholas M. Holden

Abstract The Hybrid Soil Moisture Deficit (HSMD) model has been used for a wide range of applications, including modelling of grassland productivity and utilisation, assessment of agricultural management opportunities such as slurry spreading, predicting nutrient emissions to the environment and risks of pathogen transfer to water. In the decade since its publication, various ad hoc modifications have been developed and the recent publication of the Irish Soil Information System has facilitated improved assessment of the spatial soil moisture dynamics. In this short note, we formally present a new version of the model (HSMD2.0), which includes two new soil drainage classes, as well as an optional module to account for the topographic wetness index at any location. In addition, we present a new Indicative Soil Drainage Map for Ireland, based on the Irish Soil Classification system, developed as part of the Irish Soil Information System.


Sign in / Sign up

Export Citation Format

Share Document