In order to explore the method and index of potato fine drought forecast in central Inner Mongolia,based on the data of potato yield and precipitation in Wuchuan County of Hohhot City,Guyang County of Baotou City,and ...In order to explore the method and index of potato fine drought forecast in central Inner Mongolia,based on the data of potato yield and precipitation in Wuchuan County of Hohhot City,Guyang County of Baotou City,and Chayou Middle Banner of Ulan Qab City from 1979 to 2013,the relationship between precipitation anomaly percentage and meteorological yield during potato growth period in central Inner Mongolia was analyzed by regression analysis.According to the precipitation anomaly percentage meteorological drought index,the light drought,medium drought and heavy drought indexes of the seedling stage and flowering stage in the above-mentioned areas were obtained as follows:-5%--25%,-25%--40%,and<-40%,respectively.The results show that the models are more accurate in determining the yield reduction caused by drought,and can well predict the occurrence of drought.展开更多
Droughts represent one of the most dangerous natural disasters in the world, due to their ability to progressively spread over large areas up to continental scale, as well as their adverse environmental, human and soc...Droughts represent one of the most dangerous natural disasters in the world, due to their ability to progressively spread over large areas up to continental scale, as well as their adverse environmental, human and socio-economic effects. Unfortunately, these effects are increasingly accentuated under the influence of climate change. One of the main challenges today is to mitigate the damage associated with droughts by developing tools capable of predicting the occurrence of such events in advance. Many solutions have been implemented for this purpose. But with the great progress in artificial intelligence, many scientists propose the use of Machine Learning to provide more optimal solutions to the problem related to droughts. In the present study, a bibliometric analysis was conducted to assess the current level of research on forecasting and monitoring of droughts in the world in general, particularly in West Africa through different methods based on the artificial intelligence. A search for articles on the topic was performed in the Web of Science (WoS) database, which is a global, publisher-independent citation database. The search identified a total of 3284 documents and the collected data was analyzed using a bibliometric tool called Bibliometrix. The main results are presented and discussed, followed by some potential avenues for research.展开更多
The influence of various factors, mechanisms, and principles affecting runoff are summarized as periodic law, random law, and basin-wide law. Periodic law is restricted by astronomical factors, random law is restricte...The influence of various factors, mechanisms, and principles affecting runoff are summarized as periodic law, random law, and basin-wide law. Periodic law is restricted by astronomical factors, random law is restricted by atmospheric circulation, and basin-wide law is restricted by underlying surface. The commensurability method was used to identify the almost period law, the wave method was applied to deducing the random law, and the precursor method was applied in order to forecast runoff magnitude for the current year. These three methods can be used to assess each other and to forecast runoff. The system can also be applied to forecasting wet years, normal years and dry years for a particular year as well as forecasting years when floods with similar characteristics of previous floods, can be expected. Based on hydrological climate data of Baishan (1933-2009) and Nierji (1886-2009) in the Songhua River Basin, the forecasting results for 2010 show that it was a wet year in the Baishan Reservoir, similar to the year of 1995; it was a secondary dry year in the Nierji Reservoir, similar to the year of 1980. The actual water inflow into the Baishan Reservoir was 1.178 × 10 10 m 3 in 2010, which was markedly higher than average inflows, ranking as the second highest in history since records began. The actual water inflow at the Nierji station in 2010 was 9.96 × 10 9 m 3 , which was lower than the average over a period of many years. These results indicate a preliminary conclusion that the methods proposed in this paper have been proved to be reasonable and reliable, which will encourage the application of the chief reporter release system for each basin. This system was also used to forecast inflows for 2011, indicating a secondary wet year for the Baishan Reservoir in 2011, similar to that experienced in 1991. A secondary wet year was also forecast for the Nierji station in 2011, similar to that experienced during 1983. According to the nature of influencing factors, mechanisms and forecasting methods and the service objects, mid-to long-term hydrological forecasting can be divided into two classes:mid-to long-term runoff forecasting, and severe floods and droughts forecasting. The former can be applied to quantitative forecasting of runoff, which has important applications for water release schedules. The latter, i.e., qualitative disaster forecasting, is important for flood control and drought relief. Practical methods for forecasting severe droughts and floods are discussed in this paper.展开更多
Jordan is very vulnerable to drought because of its location in the arid to semi-arid part of the Middle East. Droughts coupled with water scarcity are becoming a serious threat to the economic growth, social cohesion...Jordan is very vulnerable to drought because of its location in the arid to semi-arid part of the Middle East. Droughts coupled with water scarcity are becoming a serious threat to the economic growth, social cohesion and political stability. Rainfall time series from four rain stations covering the Jordan River Basin were analyzed for drought characterization and forecasting using standardized precipitation index (SPI), Markov chain and autoregressive integrated moving average (ARIMA) model. The 7-year moving average of Amman data showed a decreasing trend while data from the other three stations were stable or showed an increasing trend. The frequency analysis indicated 2-year return period for near zero SPI values while the return period for moderate drought was 7 years. Successive droughts had occurred at least three times during the past 40 years. Severe droughts are expected once every 20 - 25 year period at all rain stations. The extreme droughts were rare events with return periods between 80 and 115 years. There are equal occurrence probabilities for drought and wet conditions in any given year, irrespective, of the condition in the previous year. The results showed that ARIMA model was successful in predicting the overall statistics with a given period at annual scales. The overall number of predicted/observed droughts during the validation periods were 2/2 severe droughts for Amman station and, 0/1, 1/1, 0/1 extreme droughts for Amman, Irbid and Mafraq stations, respectively. In addition, the ARIMA model also predicted 3 out of 4 actual moderate droughts for Amman and Mafraq stations. It was concluded that early warning of developing droughts can be deduced form the monthly Markov transitional probabilities. ARIMA models can be used as a forecasting tool of the future drought trends. Using the first and second order Markov probabilities can complement the ARIMA predictions.展开更多
Drought is the least understood natural disaster due to the complex relationship of multiple contributory factors. Itsbeginning and end are hard to gauge, and they can last for months or even for years. India has face...Drought is the least understood natural disaster due to the complex relationship of multiple contributory factors. Itsbeginning and end are hard to gauge, and they can last for months or even for years. India has faced many droughtsin the last few decades. Predicting future droughts is vital for framing drought management plans to sustainnatural resources. The data-driven modelling for forecasting the metrological time series prediction is becomingmore powerful and flexible with computational intelligence techniques. Machine learning (ML) techniques havedemonstrated success in the drought prediction process and are becoming popular to predict the weather, especiallythe minimum temperature using backpropagation algorithms. The favourite ML techniques for weather forecastinginclude support vector machines (SVM), support vector regression, random forest, decision tree, logistic regression,Naive Bayes, linear regression, gradient boosting tree, k-nearest neighbours (KNN), the adaptive neuro-fuzzyinference system, the feed-forward neural networks, Markovian chain, Bayesian network, hidden Markov models,and autoregressive moving averages, evolutionary algorithms, deep learning and many more. This paper presentsa recent review of the literature using ML in drought prediction, the drought indices, dataset, and performancemetrics.展开更多
基金Supported by Natural Science Foundation of Inner Mongolia,China(2018MS03003)。
文摘In order to explore the method and index of potato fine drought forecast in central Inner Mongolia,based on the data of potato yield and precipitation in Wuchuan County of Hohhot City,Guyang County of Baotou City,and Chayou Middle Banner of Ulan Qab City from 1979 to 2013,the relationship between precipitation anomaly percentage and meteorological yield during potato growth period in central Inner Mongolia was analyzed by regression analysis.According to the precipitation anomaly percentage meteorological drought index,the light drought,medium drought and heavy drought indexes of the seedling stage and flowering stage in the above-mentioned areas were obtained as follows:-5%--25%,-25%--40%,and<-40%,respectively.The results show that the models are more accurate in determining the yield reduction caused by drought,and can well predict the occurrence of drought.
文摘Droughts represent one of the most dangerous natural disasters in the world, due to their ability to progressively spread over large areas up to continental scale, as well as their adverse environmental, human and socio-economic effects. Unfortunately, these effects are increasingly accentuated under the influence of climate change. One of the main challenges today is to mitigate the damage associated with droughts by developing tools capable of predicting the occurrence of such events in advance. Many solutions have been implemented for this purpose. But with the great progress in artificial intelligence, many scientists propose the use of Machine Learning to provide more optimal solutions to the problem related to droughts. In the present study, a bibliometric analysis was conducted to assess the current level of research on forecasting and monitoring of droughts in the world in general, particularly in West Africa through different methods based on the artificial intelligence. A search for articles on the topic was performed in the Web of Science (WoS) database, which is a global, publisher-independent citation database. The search identified a total of 3284 documents and the collected data was analyzed using a bibliometric tool called Bibliometrix. The main results are presented and discussed, followed by some potential avenues for research.
基金Under the auspices of National Natural Science Foundation(No.50879028)Open Fund of State Key Laboratory of Hydrology-Water Resources and Hydraulic Engineering of Nanjing Hydraulic Research institute(No.2009491311)+1 种基金Open Research Fund Program of State key Laboratory of Hydroscience and Engineering,Tsinghua University(No.sklhse-2010-A-02)Application Foundation Items of Science and Technology Department of Jilin Province(No.2011-05013)
文摘The influence of various factors, mechanisms, and principles affecting runoff are summarized as periodic law, random law, and basin-wide law. Periodic law is restricted by astronomical factors, random law is restricted by atmospheric circulation, and basin-wide law is restricted by underlying surface. The commensurability method was used to identify the almost period law, the wave method was applied to deducing the random law, and the precursor method was applied in order to forecast runoff magnitude for the current year. These three methods can be used to assess each other and to forecast runoff. The system can also be applied to forecasting wet years, normal years and dry years for a particular year as well as forecasting years when floods with similar characteristics of previous floods, can be expected. Based on hydrological climate data of Baishan (1933-2009) and Nierji (1886-2009) in the Songhua River Basin, the forecasting results for 2010 show that it was a wet year in the Baishan Reservoir, similar to the year of 1995; it was a secondary dry year in the Nierji Reservoir, similar to the year of 1980. The actual water inflow into the Baishan Reservoir was 1.178 × 10 10 m 3 in 2010, which was markedly higher than average inflows, ranking as the second highest in history since records began. The actual water inflow at the Nierji station in 2010 was 9.96 × 10 9 m 3 , which was lower than the average over a period of many years. These results indicate a preliminary conclusion that the methods proposed in this paper have been proved to be reasonable and reliable, which will encourage the application of the chief reporter release system for each basin. This system was also used to forecast inflows for 2011, indicating a secondary wet year for the Baishan Reservoir in 2011, similar to that experienced in 1991. A secondary wet year was also forecast for the Nierji station in 2011, similar to that experienced during 1983. According to the nature of influencing factors, mechanisms and forecasting methods and the service objects, mid-to long-term hydrological forecasting can be divided into two classes:mid-to long-term runoff forecasting, and severe floods and droughts forecasting. The former can be applied to quantitative forecasting of runoff, which has important applications for water release schedules. The latter, i.e., qualitative disaster forecasting, is important for flood control and drought relief. Practical methods for forecasting severe droughts and floods are discussed in this paper.
文摘Jordan is very vulnerable to drought because of its location in the arid to semi-arid part of the Middle East. Droughts coupled with water scarcity are becoming a serious threat to the economic growth, social cohesion and political stability. Rainfall time series from four rain stations covering the Jordan River Basin were analyzed for drought characterization and forecasting using standardized precipitation index (SPI), Markov chain and autoregressive integrated moving average (ARIMA) model. The 7-year moving average of Amman data showed a decreasing trend while data from the other three stations were stable or showed an increasing trend. The frequency analysis indicated 2-year return period for near zero SPI values while the return period for moderate drought was 7 years. Successive droughts had occurred at least three times during the past 40 years. Severe droughts are expected once every 20 - 25 year period at all rain stations. The extreme droughts were rare events with return periods between 80 and 115 years. There are equal occurrence probabilities for drought and wet conditions in any given year, irrespective, of the condition in the previous year. The results showed that ARIMA model was successful in predicting the overall statistics with a given period at annual scales. The overall number of predicted/observed droughts during the validation periods were 2/2 severe droughts for Amman station and, 0/1, 1/1, 0/1 extreme droughts for Amman, Irbid and Mafraq stations, respectively. In addition, the ARIMA model also predicted 3 out of 4 actual moderate droughts for Amman and Mafraq stations. It was concluded that early warning of developing droughts can be deduced form the monthly Markov transitional probabilities. ARIMA models can be used as a forecasting tool of the future drought trends. Using the first and second order Markov probabilities can complement the ARIMA predictions.
文摘Drought is the least understood natural disaster due to the complex relationship of multiple contributory factors. Itsbeginning and end are hard to gauge, and they can last for months or even for years. India has faced many droughtsin the last few decades. Predicting future droughts is vital for framing drought management plans to sustainnatural resources. The data-driven modelling for forecasting the metrological time series prediction is becomingmore powerful and flexible with computational intelligence techniques. Machine learning (ML) techniques havedemonstrated success in the drought prediction process and are becoming popular to predict the weather, especiallythe minimum temperature using backpropagation algorithms. The favourite ML techniques for weather forecastinginclude support vector machines (SVM), support vector regression, random forest, decision tree, logistic regression,Naive Bayes, linear regression, gradient boosting tree, k-nearest neighbours (KNN), the adaptive neuro-fuzzyinference system, the feed-forward neural networks, Markovian chain, Bayesian network, hidden Markov models,and autoregressive moving averages, evolutionary algorithms, deep learning and many more. This paper presentsa recent review of the literature using ML in drought prediction, the drought indices, dataset, and performancemetrics.
