Prediction of monthly rainfall in Victoria, Australia: Clusterwise linear regression approach

Bagirov, Adil M.; Mahmood, Arshad; Barton, Andrew

doi:10.1016/j.atmosres.2017.01.003

Cited by 87 publications

(46 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In terms of the research and services concerning the early drought warning, this paper is carried out by mainly adopting the statistical model, Markov chain transition probability, and by employing the precipitation-related factors, Palmer drought, and standardized precipitation indexes [13][14][15][16]. Bagirov [17] has established a multiple linear regression model using the sowing delay date, monthly precipitation and rainy days, and so forth deriving from the precipitation data in order to estimate the one month output before harvesting and has brought about a final early warning model to estimate the crop output at the time when crops are about to be harvested. The models have been further optimized and improved.…”

Section: Introductionmentioning

confidence: 99%

Evaluation on Early Drought Warning System in the Jinghui Channel Irrigation Area

Shang

Zhang

2020

IJERPH

View full text Add to dashboard Cite

With the economic growth, continuous global environment deterioration, and increasingly serious water resources shortage, droughts have become more and more serious and produced great impacts on both the regional ecology and sustainable economic development. This paper has established the “green, blue, yellow, orange, and red lights” as the early warning grades for agricultural droughts. By using the two influencing factors, namely precipitation and soil moisture, this paper has established the drought assessment index evaluation model using weighted coupling method. It has carried out the analogue simulation of the early drought warning based on the Jinghui Channel’s 2013 water source situations. The soil moisture in January and February is relatively ideal, and the actual early drought warning is expressed by the “green light”. The soil moisture deficit is comparatively serious in March, but the situation concerning water inflow is ideal with the “green light”. Actually, the early warning signal is basically consistent with the soil moisture drought degree between April and August. The actual early warning is expressed by the “green light” as well, but the soil moisture is not so ideal, however, this is the seeding time of the winter wheat so the lack of soil moisture has no impact on the crops output. In November and December, the winter wheat is at the growth and development stage and does not need much moisture. At this stage, the soil moisture is relatively poor. By integrating the time effects into the early drought warning system, this paper provides administrators of irrigation areas with a scientific decision-making based on the drought control measures.

show abstract

Section: Introductionmentioning

confidence: 99%

Evaluation on Early Drought Warning System in the Jinghui Channel Irrigation Area

Shang

Zhang

2020

IJERPH

View full text Add to dashboard Cite

show abstract

“…One of the ways to classify the data is clusterwise regression techniques. The clusterwise regression is based on the combination of these two techniques that find simultaneously an optimal partition of data in k cluster and regression function within cluster [1]. It is assumed that samples come from a certain number of populations and consider the existence of subpopulations of heterogeneous populations.…”

Section: Introductionmentioning

confidence: 99%

Clusterwise Regression Model Development with Gamma Distribution

Syafruddin¹,

Soleh²,

Wigena³

2020

Proceedings of the Proceedings of the 1st International Conference on Statistics and Analytics, ICSA 2019, 2-3 August 2019, Bog

View full text Add to dashboard Cite

This paper present development of clusterwise regression with a data set that has gamma distribution. Clusterwise regression is a method that finds simultaneously an optimal member of data in k cluster and each cluster have the best regression model. Analysis of a simulated data set has also been presented for illustrative purposes. Gamma and normal distributions were used for distribution of responses scenario with different parameters. This simulation study is carried out by initializing the number of clusters, classify observations randomly as an initial partition, move observation to the cluster giving the smallest residual and re-estimate the regression model from final partition. This simulation showed that clusterwise regression is able to form partition according to the distribution of data, also to form the best generalized linear model with Gamma distribution and linear regression model.

show abstract

“…According to results, Random Forest performed better as with small training data it correctly classified large amount of instances. In [2], researchers presented Clusterwise Linear Regression (CLR) method, which is the combination of clustering and regression techniques. The proposed technique is used to predict monthly rainfall in Victoria, Australia, by using input data of 8 [5] proposed an algorithm which combined data mining and statistical techniques.…”

Section: Related Workmentioning

confidence: 99%

Rainfall Prediction in Lahore City using Data Mining Techniques

Aftab¹,

Ahmad²,

Hameed³

et al. 2018

ijacsa

View full text Add to dashboard Cite

Abstract-Rainfall prediction has extreme significance in countless aspects and scopes. It can be very helpful to reduce the effects of sudden and extreme rainfall by taking effective security measures in advance. Due to climate variations, an accurate rainfall prediction has become more complex than before. Data mining techniques can predict the rainfall through extracting the hidden patterns among weather attributes of past data. This research contributes by exploring the use of various data mining techniques for rainfall prediction in Lahore city. Techniques include: Support Vector Machine (SVM), Naïve Bayes (NB), k Nearest Neighbor (kNN), Decision Tree (J48) and Multilayer Perceptron (MLP). The dataset is obtained from a weather forecasting website and consists of several atmospheric attributes. For effective prediction, pre-processing technique is used which consists of cleaning and normalization processes. Performance of used data mining techniques is analyzed in terms of precision, recall and f-measure with various ratios of training and test data.

show abstract

Prediction of monthly rainfall in Victoria, Australia: Clusterwise linear regression approach

Cited by 87 publications

References 29 publications

Evaluation on Early Drought Warning System in the Jinghui Channel Irrigation Area

Evaluation on Early Drought Warning System in the Jinghui Channel Irrigation Area

Clusterwise Regression Model Development with Gamma Distribution

Rainfall Prediction in Lahore City using Data Mining Techniques

Contact Info

Product

Resources

About