Agricultural Drought Prediction Based on Conditional Distributions of Vine Copulas

2021 ◽  
Author(s):  
Haijiang Wu ◽  
Xiaoling Su ◽  
Vijay P. Singh ◽  
Kai Feng ◽  
Jiping Niu
Keyword(s):  
Agricultural Drought ◽  
Conditional Distributions ◽  
Drought Prediction ◽  
Vine Copulas

Improved SVR machine learning models for agricultural drought prediction at downstream of Langat River Basin, Malaysia

2019 ◽  
Vol 11 (4) ◽  
pp. 1383-1398 ◽  
Author(s):  
Kit Fai Fung ◽  
Yuk Feng Huang ◽  
Chai Hoon Koo ◽  
Majid Mirzaei
Keyword(s):  
Support Vector Regression ◽  
River Basin ◽  
Lead Time ◽  
Model Performance ◽  
Agricultural Drought ◽  
Support Vector ◽  
Drought Prediction ◽  
Langat River ◽  
Model Training ◽  
Boosting Technique

Abstract Drought is a harmful and little understood natural hazard. Effective drought prediction is vital for sustainable agricultural activities and water resources management. The support vector regression (SVR) model and two of its enhanced variants, namely, fuzzy-support vector regression (F-SVR) and boosted-support vector regression (BS-SVR) models, for predicting the standardized precipitation evapotranspiration indices (SPEI) (in this case, SPEI-1, SPEI-3 and SPEI-6, at various timescales) with a lead time of one month, were developed to minimize potential drought impact on oil palm plantations at the downstream end of the Langat River Basin, which has a tropical climate pattern. Observed SPEIs from periods 1976 to 2011 and 2012 to 2015 were used for model training and validation, respectively. By applying the MAE, RMSE, MBE and R2 as model assessments, it was found that the F-SVR model was best with the trend of improving accuracy when the timescale of the SPEIs increased. It was also found that differences in model performance deteriorates with increased timescale of the SPEIs. The outlier reducing effect from the fuzzy concept has better improvement for the SVR-based models compared to the boosting technique in predicting SPEI-1, SPEI-3 and SPEI-6 for a one-month lead time at the downstream of Langat River Basin.

Crop and Location Specific Agricultural Drought Quantification: Part III. Forecasting Water Stress and Yield Trends

2017 ◽  
Vol 60 (3) ◽  
pp. 741-752 ◽  
Author(s):  
Rachel L. McDaniel ◽  
Clyde Munster ◽  
John Nielsen-Gammon
Keyword(s):  
Water Management ◽  
Soil Moisture ◽  
Water Stress ◽  
Water Conservation ◽  
Drought Index ◽  
Swat Model ◽  
Agricultural Drought ◽  
Weather Data ◽  
Drought Prediction ◽  
Yield Trends

Abstract. Agriculture is the largest water consumer, with 70% of global water withdrawals being used for irrigation. Water scarcity issues are being exacerbated by drought and population increases, making efficient water resource management in agricultural production increasingly important. The objective of this article is to evaluate the use of short-term weather forecasts for agricultural drought prediction. A crop-specific, linear regression drought analysis technique was used in this study. This study takes place in the upper Colorado River basin (UCRB) in west Texas. Five variables associated with agricultural drought (precipitation, temperature, biomass production, soil moisture depletion, and transpiration) were scaled and used to estimate cotton yields. The yield percentiles were used as a drought index. Precipitation and temperature were forecasted with a two-week lead time using probable scenarios based on historical data. The other three variables were estimated using the SWAT model. Forecasts were generated for each week of the growing season from 2010 through 2013. Four statistics were used to evaluate model performance, including the Nash-Sutcliffe coefficient of efficiency (NSE), the coefficient of determination (R2), and two error indices, the percent bias (PBIAS) and the RMSE-observations standard deviation ratio (RSR). Comparing the variables using the forecasted weather data to those using the observed weather data revealed that four of the five performed satisfactorily. Temperature performed the best statistically, with an NSE of 0.85 and PBIAS of 9.4%. Precipitation (NSE = 0.51, PBIAS = -34%), cumulative biomass (NSE = 0.69, PBIAS = -38%), and transpiration (NSE = 0.53, PBIAS = 11%) also performed well. However, the soil moisture depletion forecasts (NSE = 0.28, PBIAS = 11%) were unsatisfactory. The forecasted cotton yield trends (NSE = 0.72, PBIAS = -12%) and drought index (NSE = 0.76, PBIAS = -13%) both performed satisfactorily, indicating that this forecasting method may be used for decision making related to agricultural water management, including irrigation timing. Keywords: Crop modeling, Drought, Drought index, Forecasting, Hydrologic modeling, SWAT, Water conservation, Water management, Water stress.

scholarly journals Evaluation of a combined drought indicator and its potential for agricultural drought prediction in southern Spain

2020 ◽  
Vol 20 (1) ◽  
pp. 21-33 ◽  
Author(s):  
María del Pilar Jiménez-Donaire ◽  
Ana Tarquis ◽  
Juan Vicente Giráldez
Keyword(s):  
Soil Moisture ◽  
Vegetation Index ◽  
Standardized Precipitation Index ◽  
Agricultural Drought ◽  
Crop Damage ◽  
Rainfall Regime ◽  
Type I ◽  
Drought Prediction ◽  
Mediterranean Countries ◽  
Four Levels

Abstract. Drought prediction is crucial, especially where the rainfall regime is irregular, such as in Mediterranean countries. A new combined drought indicator (CDI) integrating rainfall, soil moisture and vegetation dynamics is proposed. Standardized precipitation index (SPI) is used for evaluating rainfall trends. A bucket-type soil moisture model is employed for keeping track of soil moisture and calculating anomalies, and, finally, satellite-based normalized difference vegetation index (NDVI) data are used for monitoring vegetation response. The proposed CDI has four levels, at increasing degrees of severity: watch, warning, alert type I and alert type II. This CDI was thus applied over the period 2003–2013 to five study sites, representative of the main grain-growing areas of SW Spain. The performance of the CDI levels was assessed by comparison with observed crop damage data. Observations show a good match between crop damage and the CDI. Important crop drought events in 2004–2005 and 2011–2012, distinguished by crop damage in between 70 % and 95 % of the total insured area, were correctly predicted by the proposed CDI in all five areas.

A novel hybrid dragonfly optimization algorithm for agricultural drought prediction

2021 ◽  
Author(s):  
Pouya Aghelpour ◽  
Babak Mohammadi ◽  
Saeid Mehdizadeh ◽  
Hadigheh Bahrami-Pichaghchi ◽  
Zheng Duan
Keyword(s):  
Optimization Algorithm ◽  
Agricultural Drought ◽  
Drought Prediction

Development of a distributed agricultural drought prediction model based on TOPMODEL and GIS

2009 ◽  
Author(s):  
Jingwen Xu ◽  
Wanchang Zhang ◽  
Changquan Wang ◽  
Xuemei Zhu ◽  
Jiongfeng Chen
Keyword(s):  
Prediction Model ◽  
Agricultural Drought ◽  
Model Based ◽  
Drought Prediction

Drought Analysis Based on the Information Diffusion and Fractal Technology: A Case Study of Winter Wheat in China

2020 ◽  
Vol 36 (6) ◽  
pp. 869-877
Author(s):  
Jian-bin Yao ◽  
Jian-hua Liu ◽  
Hui-jie Ma ◽  
Hong-wei Pan
Keyword(s):  
Winter Wheat ◽  
Information Diffusion ◽  
Fractal Theory ◽  
Meteorological Drought ◽  
Agricultural Drought ◽  
Data Series ◽  
List Type ◽  
Drought Forecasting ◽  
Study Region ◽  
Drought Prediction

HighlightsThere is no good correlation between meteorological drought and crop drought.The data series of meteorological drought and crop drought at the same time have fractal characteristics.Fractal theory can be used to predict the next drought year.Abstract.Drought is one of the natural disasters of global concern. Drought forecasting is an important tool for drought management. Uncertainty is a major challenge in drought forecasting. In order to provide a short-term effective drought prediction, this study provides a new point into drought prediction from the timing-prediction perspective. The key part of this essay lies in its fractal theoretical framework guided by the self-similarity principle, which fully considers the complexity, disorder and regularity of agricultural drought. At the same time, information diffusion theory is used to polish the raw data, especially some data about winter wheat in Zhengzhou in China. The results as follows: 1) the change trend of drought in the study region is consistent with the past; 2) the time of meteorological drought, summer maize does not necessarily lead to drought, but most timing prediction work is consistent, they have shared the similar cyclical changing-laws; and 3) the occurring time of the next drought calculated is consistent with the actual observation results. Therefore, the method established in this study is effective, and it can provide some reference for the prediction of agricultural drought outbreak time. Keywords: Crop drought, Fractal theory, Information diffusion, Meteorological drought, Winter wheat.

Sign in / Sign up

Export Citation Format

Share Document