DroughtCast: A Machine Learning Forecast of the United States Drought Monitor

Drought is one of the most ecologically and economically devastating natural phenomena affecting the United States, causing the U.S. economy billions of dollars in damage, and driving widespread degradation of ecosystem health. Many drought indices are implemented to monitor the current extent and status of drought so stakeholders such as farmers and local governments can appropriately respond. Methods to forecast drought conditions weeks to months in advance are less common but would provide a more effective early warning system to enhance drought response, mitigation, and adaptation planning. To resolve this issue, we introduce DroughtCast, a machine learning framework for forecasting the United States Drought Monitor (USDM). DroughtCast operates on the knowledge that recent anomalies in hydrology and meteorology drive future changes in drought conditions. We use simulated meteorology and satellite observed soil moisture as inputs into a recurrent neural network to accurately forecast the USDM between 1 and 12 weeks into the future. Our analysis shows that precipitation, soil moisture, and temperature are the most important input variables when forecasting future drought conditions. Additionally, a case study of the 2017 Northern Plains Flash Drought shows that DroughtCast was able to forecast a very extreme drought event up to 12 weeks before its onset. Given the favorable forecasting skill of the model, DroughtCast may provide a promising tool for land managers and local governments in preparing for and mitigating the effects of drought.

Download Full-text

Operational Near-real Time Drought Monitoring Using Global Satellite Precipitation Estimates

10.5194/egusphere-egu2020-14871 ◽

2020 ◽

Author(s):

Olivier Prat ◽

Alec Courtright ◽

Ronald Leeper ◽

Brian Nelson ◽

Rocky Bilotta ◽

...

Keyword(s):

United States ◽

Real Time ◽

The United States ◽

Global Scale ◽

Drought Monitoring ◽

Drought Indices ◽

In Situ Data ◽

Drought Conditions ◽

Precipitation Estimates ◽

Monitoring Information

<p>We present an operational near-real time drought monitoring framework on a global scale that uses satellite quantitative precipitation estimates from the NOAA/CDR program (CMORPH-CDR, PERSIANN-CDR). Monthly and daily Standardized Precipitation Indexes (SPI) are computed for various time scales over the entire period of record of the respective datasets. The near-real time availability of CMORPH-CDR permits for a daily update of the global drought conditions starting in 1998, while the longer period of record of PERSIANN-CDR allows to compute global drought conditions since 1983. The SPI sensitivity to different precipitation datasets and to various lengths of record is quantified. Results indicated that both monthly and daily SPIs computed with both CDRs presented the same timing and area for the major droughts episodes over the continental United States as well as for selected drought events around the globe. Furthermore, the difference resulting from the use of the two-parameter Gamma distribution (McKee et al. 1993) and the three-parameter Pearson III distribution (Guttman 1999) is evaluated. The global mapping of the different distribution parameters (2 and 3 parameters respectively for the Gamma and Pearson III distributions) informs us on how to optimally compute the SPI in areas experiencing too much or too little rainfall. Both CMORPH-CDR and PERSIANN-CDR SPIs are evaluated primarily over CONUS where long-term drought monitoring products based on in-situ data exists such as the United States Drought Monitor (USDM) and the nClimGrid derived SPI. A publicly available interactive visualization tool that provides access to global drought information is also presented. The tools is intended to fill some of the drought monitoring information gaps around the globe. A variety of visualization techniques are used to aid in the interpretation of global drought indices while interactive functionality allows users to focus on a specific region and time-scale of interest. Additional information for region specific drought monitoring resources is also provided to help users access regional drought monitoring information.</p>

Download Full-text

Flash Drought Characteristics Based on U.S. Drought Monitor

Atmosphere ◽

10.3390/atmos10090498 ◽

2019 ◽

Vol 10 (9) ◽

pp. 498 ◽

Cited By ~ 7

Author(s):

L. Gwen Chen ◽

Jon Gottschalck ◽

Adam Hartman ◽

David Miskus ◽

Rich Tinker ◽

...

Keyword(s):

United States ◽

Soil Moisture ◽

Warm Season ◽

The United States ◽

Rate Of Change ◽

Disaster Mitigation ◽

Drought Event ◽

Central United States ◽

Fast Development ◽

Moisture Conditions

Understanding the characteristics of flash drought events and further predicting the onset of such events on subseasonal timescales is of critical importance for impact assessment, disaster mitigation, and loss prevention. In this study, we employ a rate-of-change approach and define a flash drought event as a drought event with greater than or equal to two categories degradation in a four-week period based on the U.S. Drought Monitor. Unlike conventional drought, which can occur year-round and everywhere in the United States, flash drought has preferred seasons and locations to occur, mostly in the warm season and over the central United States. Widespread flash drought over the United States is largely correlated with La Niña episodes. In contrast with conventional drought, which is mainly driven by precipitation deficits, anomalously high evapotranspiration rates, caused by anomalously high temperatures, winds, and/or incoming radiation, are usually present before the onset of flash drought. Comparing to precipitation and soil moisture, evapotranspiration typically has the largest decline rate during the fast-development phase. Three-month Standardized Precipitation Indexes are mostly dry right before flash drought onset, but large deficits are not required. As a result, monitoring rapid changes in evapotranspiration, along with precipitation and soil moisture conditions, can provide early warnings of flash drought development.

Download Full-text

Model-Based Drought Indices over the United States

Journal of Hydrometeorology ◽

10.1175/2008jhm1002.1 ◽

2008 ◽

Vol 9 (6) ◽

pp. 1212-1230 ◽

Cited By ~ 110

Author(s):

Kingtse C. Mo

Keyword(s):

United States ◽

Soil Moisture ◽

Standardized Precipitation Index ◽

Meteorological Drought ◽

The United States ◽

Horizontal Resolution ◽

Agricultural Drought ◽

Drought Indices ◽

Eastern United States ◽

Infiltration Capacity

Abstract Drought indices derived from the North American Land Data Assimilation System (NLDAS) Variable Infiltration Capacity (VIC) and Noah models from 1950 to 2000 are intercompared and evaluated for their ability to classify drought across the United States. For meteorological drought, the standardized precipitation index (SPI) is used to measure precipitation deficits. The standardized runoff index (SRI), which is similar to the SPI, is used to classify hydrological drought. Agricultural drought is measured by monthly-mean soil moisture (SM) anomaly percentiles based on probability distributions (PDs). The PDs for total SM are regionally dependent and influenced by the seasonal cycle, but the PDs for SM monthly-mean anomalies are unimodal and Gaussian. Across the eastern United States (east of 95°W), the indices derived from VIC and Noah are similar, and they are able to detect the same drought events. Indices are also well correlated. For river forecast centers (RFCs) across the eastern United States, different drought indices are likely to detect the same drought events. The monthly-mean soil moisture (SM) percentiles and runoff indices between VIC and Noah have large differences across the western interior of the United States. For small areas with a horizontal resolution of 0.5° on the time scales of one to three months, the differences of SM percentiles and SRI between VIC and Noah are larger than the thresholds used to classify drought. For the western RFCs, drought events selected according to SM percentiles or SRI derived from different NLDAS systems do not always overlap.

Download Full-text

Multi-layer high-resolution soil moisture estimation using machine learning over the United States

Remote Sensing of Environment ◽

10.1016/j.rse.2021.112706 ◽

2021 ◽

Vol 266 ◽

pp. 112706

Author(s):

L. Karthikeyan ◽

Ashok K. Mishra

Keyword(s):

United States ◽

Machine Learning ◽

Soil Moisture ◽

High Resolution ◽

The United States ◽

Moisture Estimation

Download Full-text

Bringing the Real World of Science to Children: A Partnership of the American Museum of Natural History and the City University of New York

Online Learning ◽

10.24059/olj.v12i1.43 ◽

2008 ◽

Vol 12 (1) ◽

Cited By ~ 1

Author(s):

Anthony G Picciano ◽

Robert V. Steiner

Keyword(s):

United States ◽

New York ◽

Natural History ◽

Local Governments ◽

Compulsory Education ◽

Development Program ◽

The United States ◽

American Museum ◽

The World ◽

The City

Every child has a right to an education. In the United States, the issue is not necessarily about access to a school but access to a quality education. With strict compulsory education laws, more than 50 million students enrolled in primary and secondary schools, and billions of dollars spent annually on public and private education, American children surely have access to buildings and classrooms. However, because of a complex and competitive system of shared policymaking among national, state, and local governments, not all schools are created equal nor are equal education opportunities available for the poor, minorities, and underprivileged. One manifestation of this inequity is the lack of qualified teachers in many urban and rural schools to teach certain subjects such as science, mathematics, and technology. The purpose of this article is to describe a partnership model between two major institutions (The American Museum of Natural History and The City University of New York) and the program designed to improve the way teachers are trained and children are taught and introduced to the world of science. These two institutions have partnered on various projects over the years to expand educational opportunity especially in the teaching of science. One of the more successful projects is Seminars on Science (SoS), an online teacher education and professional development program, that connects teachers across the United States and around the world to cutting-edge research and provides them with powerful classroom resources. This article provides the institutional perspectives, the challenges and the strategies that fostered this partnership.

Download Full-text

Descriptors of Cytochrome Inhibitors and Useful Machine Learning Based Methods for the Design of Safer Drugs

Pharmaceuticals ◽

10.3390/ph14050472 ◽

2021 ◽

Vol 14 (5) ◽

pp. 472

Author(s):

Tyler C. Beck ◽

Kyle R. Beck ◽

Jordan Morningstar ◽

Menny M. Benjamin ◽

Russell A. Norris

Keyword(s):

United States ◽

Machine Learning ◽

Drug Interactions ◽

The United States ◽

Structural Features ◽

Physiochemical Properties ◽

Drug Dosing ◽

Therapeutic Outcomes ◽

Cyp Inhibition ◽

Cyp Inhibitors

Roughly 2.8% of annual hospitalizations are a result of adverse drug interactions in the United States, representing more than 245,000 hospitalizations. Drug–drug interactions commonly arise from major cytochrome P450 (CYP) inhibition. Various approaches are routinely employed in order to reduce the incidence of adverse interactions, such as altering drug dosing schemes and/or minimizing the number of drugs prescribed; however, often, a reduction in the number of medications cannot be achieved without impacting therapeutic outcomes. Nearly 80% of drugs fail in development due to pharmacokinetic issues, outlining the importance of examining cytochrome interactions during preclinical drug design. In this review, we examined the physiochemical and structural properties of small molecule inhibitors of CYPs 3A4, 2D6, 2C19, 2C9, and 1A2. Although CYP inhibitors tend to have distinct physiochemical properties and structural features, these descriptors alone are insufficient to predict major cytochrome inhibition probability and affinity. Machine learning based in silico approaches may be employed as a more robust and accurate way of predicting CYP inhibition. These various approaches are highlighted in the review.

Download Full-text

Field-Scale Soil Moisture Retrieval Using PALSAR-2 Polarimetric Decomposition and Machine Learning

Agronomy ◽

10.3390/agronomy11010035 ◽

2020 ◽

Vol 11 (1) ◽

pp. 35

Author(s):

Xiaodong Huang ◽

Beth Ziniti ◽

Michael H. Cosh ◽

Michele Reba ◽

Jinfei Wang ◽

...

Keyword(s):

Machine Learning ◽

Soil Moisture ◽

Canopy Cover ◽

The United States ◽

Optical Data ◽

Study Region ◽

Model Based ◽

Key Indicator ◽

Ground Measurement ◽

L Band

Soil moisture is a key indicator to assess cropland drought and irrigation status as well as forecast production. Compared with the optical data which are obscured by the crop canopy cover, the Synthetic Aperture Radar (SAR) is an efficient tool to detect the surface soil moisture under the vegetation cover due to its strong penetration capability. This paper studies the soil moisture retrieval using the L-band polarimetric Phased Array-type L-band SAR 2 (PALSAR-2) data acquired over the study region in Arkansas in the United States. Both two-component model-based decomposition (SAR data alone) and machine learning (SAR + optical indices) methods are tested and compared in this paper. Validation using independent ground measurement shows that the both methods achieved a Root Mean Square Error (RMSE) of less than 10 (vol.%), while the machine learning methods outperform the model-based decomposition, achieving an RMSE of 7.70 (vol.%) and R2 of 0.60.

Download Full-text

CIKM 2020 conference report

ACM SIGWEB Newsletter ◽

10.1145/3460304.3460305 ◽

2021 ◽

pp. 1-4

Author(s):

Mathieu D'Aquin ◽

Stefan Dietze

Keyword(s):

United States ◽

Machine Learning ◽

Knowledge Management ◽

Information Retrieval ◽

Conference Report ◽

The United States ◽

Knowledge Based ◽

The World ◽

Science Conference ◽

Information And Knowledge Management

The 29th ACM International Conference on Information and Knowledge Management (CIKM) was held online from the 19 th to the 23 rd of October 2020. CIKM is an annual computer science conference, focused on research at the intersection of information retrieval, machine learning, databases as well as semantic and knowledge-based technologies. Since it was first held in the United States in 1992, 28 conferences have been hosted in 9 countries around the world.

Download Full-text