TY - JOUR
T1 - Using satellite remote sensing and machine learning techniques towards precipitation prediction and vegetation classification
AU - Stampoulis, D.
AU - Damavandi, H. G.
AU - Boscovic, D.
AU - Sabo, J.
N1 - Funding Information:
Acknowledgement. This work was supported by the National Science Foundation award (grant: GR10458) and conducted at Future H2O, Office of Knowledge Enterprise Development (OKED) at Arizona State University. The authors would like to acknowledge and appreciate Dr. Francis J. Turk from the Jet Propulsion Laboratory (JPL) and Dr. Li Li from the Naval Research Laboratory (NRL) for providing the WindSat data.
Funding Information:
This work was supported by the National Science Foundation award (grant: GR10458) and conducted at Future H2O, Office of Knowledge Enterprise Development (OKED) at Arizona Sta-te University. The authors would like to acknowledge and appreciate Dr. Francis J. Turk from theJet Propulsion Laboratory (JPL) and Dr. Li Li from the Naval Research Laboratory (NRL) for providing the WindSat data.
Publisher Copyright:
© 2020ISEIS All rights reserved.
PY - 2021
Y1 - 2021
N2 - The spatial distribution, magnitude and timing of precipitation events are being altered globally, often leading to extreme hydrologic conditions with serious implications to ecosystem services, water, food and energy security, as well as the welfare of billions of people. Motivated by the pressing need to understand, from a hydro-ecological perspective, how the dynamic nature of the hydrologic cycle will impact the environment in water-stressed regions, we implemented a novel approach that predicts precipitation spatio-temporal trends over the drought-burdened region of East Africa, based on other major hydrological components, such as vegetation water content (VWC), soil moisture (SM) and surface temperature (ST). The spatial patterns and characteristics of the inter-relations among the four aforementioned hydrologic variables were investigated over regions of East Africa characterized by different vegetation typesand for various precipitation intensity rates during 2003~ 2011. To this end, we analyzed multi-year satellite microwave remote sensing observa-tions of SM, ST, and VWC (derived from Naval Research Laboratory's WindSat radiometer) as well as their response to precipitation patterns (derived from NASA's TRMM 3B42 V7). We categorized precipitation into four bins (ranges) of intensity and trained five different state-of-the-art machine learning models for each of these categories. The models were then applied to predict the spatio-temporal precipitation dynamics over this complex region. Specifically, the Random Forest and Linear Regression models outperformed the others with the normalized mean absolute error being less than 27% for all of the categories. The characteristics of the predicted pre-cipitation were in turn used to classify vegetation regimes in East Africa. Our results indicate significant discrepancies in the performance of the models with varying values in the predicting skill as well as their ability to accurately classify vegetation into different types. Our predictive models were able to forecast the three vegetation regimes,i.e.,Forest/Woody Savanna, Savanna/Grasslands and Shrubland,with precision rate of at least 81% for all of the aforementioned precipitation bins.
AB - The spatial distribution, magnitude and timing of precipitation events are being altered globally, often leading to extreme hydrologic conditions with serious implications to ecosystem services, water, food and energy security, as well as the welfare of billions of people. Motivated by the pressing need to understand, from a hydro-ecological perspective, how the dynamic nature of the hydrologic cycle will impact the environment in water-stressed regions, we implemented a novel approach that predicts precipitation spatio-temporal trends over the drought-burdened region of East Africa, based on other major hydrological components, such as vegetation water content (VWC), soil moisture (SM) and surface temperature (ST). The spatial patterns and characteristics of the inter-relations among the four aforementioned hydrologic variables were investigated over regions of East Africa characterized by different vegetation typesand for various precipitation intensity rates during 2003~ 2011. To this end, we analyzed multi-year satellite microwave remote sensing observa-tions of SM, ST, and VWC (derived from Naval Research Laboratory's WindSat radiometer) as well as their response to precipitation patterns (derived from NASA's TRMM 3B42 V7). We categorized precipitation into four bins (ranges) of intensity and trained five different state-of-the-art machine learning models for each of these categories. The models were then applied to predict the spatio-temporal precipitation dynamics over this complex region. Specifically, the Random Forest and Linear Regression models outperformed the others with the normalized mean absolute error being less than 27% for all of the categories. The characteristics of the predicted pre-cipitation were in turn used to classify vegetation regimes in East Africa. Our results indicate significant discrepancies in the performance of the models with varying values in the predicting skill as well as their ability to accurately classify vegetation into different types. Our predictive models were able to forecast the three vegetation regimes,i.e.,Forest/Woody Savanna, Savanna/Grasslands and Shrubland,with precision rate of at least 81% for all of the aforementioned precipitation bins.
KW - Linear regression
KW - Machine learning
KW - Passive microwave remote sensing
KW - Precipitation
KW - Random forest
KW - Soil moisture
KW - Surface temperature
KW - Vegetation water content
UR - http://www.scopus.com/inward/record.url?scp=85100793282&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85100793282&partnerID=8YFLogxK
U2 - 10.3808/jei.202000427
DO - 10.3808/jei.202000427
M3 - Article
AN - SCOPUS:85100793282
VL - 37
SP - 1
EP - 15
JO - Journal of Environmental Informatics
JF - Journal of Environmental Informatics
SN - 1726-2135
IS - 1
ER -