Long-term seasonal rainfall forecasting: efficiency of linear modelling technique

The objective of this research is the assessment of the efficiency of a non-linear regression technique in predicting long-term seasonal rainfall. The non-linear models were developed using the lagged (past) values of the climate drivers, which have a significant correlation with rainfall. More specifically, the capabilities of SEIO (South-eastern Indian Ocean) and ENSO (El Nino Southern Oscillation) were assessed in reproducing the rainfall characteristics using the non-linear regression approach. The non-linear models developed were tested using the individual data sets, which were not used during the calibration of the models. The models were assessed using the commonly used statistical parameters, such as Pearson correlations (R), root mean square error (RMSE), mean absolute error (MAE) and index of agreement (d). Three rainfall stations located in the Australian Capital Territory (ACT) were selected as a case study. The analysis suggests that the predictors which has the highest correlation with the predictands do not necessarily produce the least errors in rainfall forecasting. The non-linear regression was able to predict seasonal rainfall with correlation coefficients varying from 0.71 to 0.91. The outcomes of the analysis will help the watershed management authorities to adopt efficient modelling technique by predicting long-term seasonal rainfall.

Download Full-text

Incorporating large-scale atmospheric variables in long-term seasonal rainfall forecasting using artificial neural networks: an application to the Ping Basin in Thailand

Hydrology Research ◽

10.2166/nh.2016.212 ◽

2016 ◽

Vol 48 (3) ◽

pp. 867-882 ◽

Cited By ~ 8

Author(s):

M. S. Babel ◽

T. A. J. G. Sirisena ◽

N. Singhrattna

Keyword(s):

Climate Change ◽

General Circulation ◽

Large Scale ◽

Resource Planning ◽

Seasonal Rainfall ◽

Annual Rainfall ◽

Rainfall Forecasting ◽

Artificial Neural ◽

Atmospheric Variables

Understanding long-term seasonal or annual or inter-annual rainfall variability and its relationship with large-scale atmospheric variables (LSAVs) is important for water resource planning and management. In this study, rainfall forecasting models using the artificial neural network technique were developed to forecast seasonal rainfall in May–June–July (MJJ), August–September–October (ASO), November–December–January (NDJ), and February–March–April (FMA) and to determine the effects of climate change on seasonal rainfall. LSAVs, temperature, pressure, wind, precipitable water, and relative humidity at different lead times were identified as the significant predictors. To determine the impacts of climate change the predictors obtained from two general circulation models, CSIRO Mk3.6 and MPI-ESM-MR, were used with quantile mapping bias correction. Our results show that the models with the best performance for FMA and MJJ seasons are able to forecast rainfall one month in advance for these seasons and the best models for ASO and NDJ seasons are able do so two months in advance. Under the RCP4.5 scenario, a decreasing trend of MJJ rainfall and an increasing trend of ASO rainfall can be observed from 2011 to 2040. For the dry season, while NDJ rainfall decreases, FMA rainfall increases for the same period of time.

Download Full-text

An Enhanced Multiple Linear Regression Model for Seasonal Rainfall Prediction

International Journal of Sensors Wireless Communications and Control ◽

10.2174/2210327910666191218124350 ◽

2020 ◽

Vol 10 (4) ◽

pp. 473-483

Author(s):

Pundra Chandra Shaker Reddy ◽

Alladi Sureshbabu

Keyword(s):

Linear Regression ◽

Regression Model ◽

Multiple Linear Regression ◽

Linear Regression Model ◽

Weather Prediction ◽

Big Data Analytics ◽

Multiple Linear Regression Model ◽

Seasonal Rainfall ◽

Climate Data ◽

Rainfall Forecasting

Aims & Background: India is a country which has exemplary climate circumstances comprising of different seasons and topographical conditions like high temperatures, cold atmosphere, and drought, heavy rainfall seasonal wise. These utmost varieties in climate make us exact weather prediction is a challenging task. Majority people of the country depend on agriculture. Farmers require climate information to decide the planting. Weather prediction turns into an orientation in farming sector to deciding the start of the planting season and furthermore quality and amount of their harvesting. One of the variables are influencing agriculture is rainfall. Objectives & Methods: The main goal of this project is early and proper rainfall forecasting, that helpful to people who live in regions which are inclined natural calamities such as floods and it helps agriculturists for decision making in their crop and water management using big data analytics which produces high in terms of profit and production for farmers. In this project, we proposed an advanced automated framework called Enhanced Multiple Linear Regression Model (EMLRM) with MapReduce algorithm and Hadoop file system. We used climate data from IMD (Indian Metrological Department, Hyderabad) in 1901 to 2002 period. Results: Our experimental outcomes demonstrate that the proposed model forecasting the rainfall with better accuracy compared with other existing models. Conclusion: The results of the analysis will help the farmers to adopt effective modeling approach by anticipating long-term seasonal rainfall.

Download Full-text

Long-lead seasonal rainfall forecasting using time-delay recurrent neural networks: a case study

Hydrological Processes ◽

10.1002/hyp.6571 ◽

2007 ◽

Vol 22 (2) ◽

pp. 229-241 ◽

Cited By ~ 23

Author(s):

Mohammad Karamouz ◽

Saman Razavi ◽

Shahab Araghinejad

Keyword(s):

Neural Networks ◽

Time Delay ◽

Recurrent Neural Networks ◽

Seasonal Rainfall ◽

Rainfall Forecasting

Download Full-text

Seasonal rainfall forecasting in West Africa

Nature ◽

10.1038/248464a0 ◽

1974 ◽

Vol 248 (5448) ◽

pp. 464-464 ◽

Cited By ~ 8

Author(s):

Derek Winstanley

Keyword(s):

West Africa ◽

Seasonal Rainfall ◽

Rainfall Forecasting

Download Full-text

Use of ENSO-Based Seasonal Rainfall Forecasting for Informed Cropping Decisions by Farmers in the SAT India

Climate Prediction and Agriculture ◽

10.1007/978-3-540-44650-7_17 ◽

2007 ◽

pp. 165-180 ◽

Cited By ~ 1

Author(s):

V. Nageswara Rao ◽

P. Singh ◽

J. Hansen ◽

T. Giridhara Krishna ◽

S. K. Krishna Murthy

Keyword(s):

Seasonal Rainfall ◽

Rainfall Forecasting

Download Full-text

Analysing lagged ENSO and IOD as potential predictors for long-term rainfall forecasting using multiple regression modelling

Piantadosi, J., Anderssen, R.S. and Boland J. (eds) MODSIM2013, 20th International Congress on Modelling and Simulation ◽

10.36334/modsim.2013.l8.mekanik ◽

2013 ◽

Keyword(s):

Multiple Regression ◽

Rainfall Forecasting ◽

Regression Modelling

Download Full-text

Analysis of Long-Term Trends of Annual and Seasonal Rainfall in the Awash River Basin, Ethiopia

Water ◽

10.3390/w11071498 ◽

2019 ◽

Vol 11 (7) ◽

pp. 1498 ◽

Cited By ~ 2

Author(s):

Solomon Mulugeta ◽

Clifford Fedler ◽

Mekonen Ayana

Keyword(s):

Climate Change ◽

River Basin ◽

Summer Rainfall ◽

Seasonal Rainfall ◽

Winter Rainfall ◽

Adaptation Measures ◽

Awash River Basin ◽

Long Term Trends ◽

Increasing Trends

With climate change prevailing around the world, understanding the changes in long-term annual and seasonal rainfall at local scales is very important in planning for required adaptation measures. This is especially true for areas such as the Awash River basin where there is very high dependence on rain- fed agriculture characterized by frequent droughts and subsequent famines. The aim of the study is to analyze long-term trends of annual and seasonal rainfall in the Awash River Basin, Ethiopia. Monthly rainfall data extracted from Climatic Research Unit (CRU 4.01) dataset for 54 grid points representing the entire basin were aggregated to find the respective areal annual and seasonal rainfall time series for the entire basin and its seven sub-basins. The Mann-Kendall (MK) test and Sen Slope estimator were applied to the time series for detecting the trends and for estimating the rate of change, respectively. The Statistical software package R version 3.5.2 was used for data extraction, data analyses, and plotting. Geographic information system (GIS) package was also used for grid making, site selection, and mapping. The results showed that no significant trend (at α = 0.05) was identified in annual rainfall in all sub-basins and over the entire basin in the period (1902 to 2016). However, the results for seasonal rainfall are mixed across the study areas. The summer rainfall (June through September) showed significant decreasing trend (at α ≤ 0.1) over five of the seven sub-basins at a rate varying from 4 to 7.4 mm per decade but it showed no trend over the two sub-basins. The autumn rainfall (October through January) showed no significant trends over four of the seven sub-basins but showed increasing trends over three sub-basins at a rate varying from 2 to 5 mm per decade. The winter rainfall (February through May) showed no significant trends over four sub-basins but showed significant increasing trends (at α ≤ 0.1) over three sub-basins at a rate varying from 0.6 to 2.7 mm per decade. At the basin level, the summer rainfall showed a significant decreasing trend (at α = 0.05) while the autumn and winter rainfall showed no significant trends. In addition, shift in some amount of summer rainfall to winter and autumn season was noticed. It is evident that climate change has shown pronounced effects on the trends and patterns of seasonal rainfall. Thus, the study contribute to better understanding of climate change in the basin and the information from the study can be used in planning for adaptation measures against a changing climate.

Download Full-text

Identification of possible dynamical drivers for long-term changes in temperature and rainfall patterns over Europe

Theoretical and Applied Climatology ◽

10.1007/s00704-020-03373-3 ◽

2020 ◽

Vol 143 (1-2) ◽

pp. 177-191

Author(s):

Peter Hoffmann ◽

Arne Spekat

Keyword(s):

Decadal Variability ◽

Meteorological Data ◽

Weather Type ◽

Seasonal Rainfall ◽

Weather Types ◽

Temperature And Precipitation ◽

Long Term Changes ◽

Rainfall Patterns ◽

Climate Station

AbstractThis study looks into the question to what extent long-term change patterns of observed temperature and rainfall over Europe can be attributed to dynamical causes, in other words: Are the observed changes due to a change in frequency of the patterns or have the patterns’ dynamical properties changed? By using a combination of daily meteorological data and a European weather-type classification, the long-term monthly mean temperature and precipitation were calculated for each weather-type. Subsequently, the observed weather-type sequences were used to construct analogue time series for temperature and precipitation which only include the dynamical component of the long-term variability since 1961. The results show that only a fraction of about 20% of the past temperature rise since 1990, which for example amounted to 1 °C at the Potsdam Climate Station can be explained by dynamical changes, i.e. most of the weather-types have become warmer. Concerning long-term changes of seasonal rainfall patterns, a fraction of more than 60% is considerably higher. Moreover, the results indicate that for rainfall compared with temperature, the decadal variability and trends of the dynamical component follow the observed ones much stronger. Consequently, most of the explained seasonal rainfall variances can be linked to changes in weather-type sequences in Potsdam and over Europe. The dynamical contribution to long-term changes in annual and seasonal rainfall patterns dominates due to the fact that the alternation of wet and dry weather-types (e.g. the types Trough or High pressure over Central Europe), their frequencies and duration has significantly changed in the last decades.

Download Full-text