An extensive evaluation of seven machine learning methods for rainfall prediction in weather derivatives

Abstract

Regression problems provide some of the most challenging research opportunities in the area of machine learning, and more broadly intelligent systems, where the predictions of some target variables are critical to a specific application. Rainfall is a prime example, as it exhibits unique characteristics of high volatility and chaotic patterns that do not exist in other time series data. This work's main impact is to show the benefit machine learning algorithms, and more broadly intelligent systems have over the current state-of-the-art techniques for rainfall prediction within rainfall derivatives. We apply and compare the predictive performance of the current state-of-the-art (Markov chain extended with rainfall prediction) and six other popular machine learning algorithms, namely: Genetic Programming, Support Vector Regression, Radial Basis Neural Networks, M5 Rules, M5 Model trees, and k-Nearest Neighbours. To assist in the extensive evaluation, we run tests using the rainfall time series across data sets for 42 cities, with very diverse climatic features. This thorough examination shows that the machine learning methods are able to outperform the current state-of-the-art. Another contribution of this work is to detect correlations between different climates and predictive accuracy. Thus, these results show the positive effect that machine learning-based intelligent systems have for predicting rainfall based on predictive accuracy and with minimal correlations existing across climates.

Modeling Dengue vector population using remotely sensed data and machine learning

“…Cross validation [50,49] was used in order to decrease the dependency of the evaluation results on a particular selection of training set and validation set pair. In particular, a time series split cross validation procedure was used to evaluate the models http://scikit-learn.org/stable/modules/ In the following we describe the techniques used to model the oviposition z-score as a function of the remotely sensed environmental variables.…”

Data Mining and Machine Learning to Promote Smart Cities: A Systematic Review from 2000 to 2018

“…Yuan et al [22] T-Drive: Enhancing Driving Directions with Taxi Drivers' Intelligence Rudin et al [23] Machine Learning for the New York City Power Grid Jurado et al [24] Hybrid methodologies for electricity load forecasting: Entropy-based feature selection with machine learning and soft computing techniques Pérez-Chacón et al [25] Big data analytics for discovering electricity consumption patterns in smart cities Peña et al [26] Rule-based system to detect energy efficiency anomalies in smart buildings, a data mining approach Liu et al [27] A machine learning-based method for the large-scale evaluation of the qualities of the urban environment Muhammed et al [28] UbeHealth: A Personalized Ubiquitous Cloud and Edge-Enabled Networked Healthcare System for Smart Cities Massana et al [29] Identifying services for short-term load forecasting using data driven models in a Smart city platform Wang et al [30] Identification of key energy efficiency drivers through global city benchmarking: a data driven approach Abbasi and El Hanandeh [31] Forecasting municipal solid waste generation using artificial intelligence modelling approaches Badii et al [32] Predicting Available Parking Slots on Critical and Regular Services by Exploiting a Range of Open Data Madu et al [33] Urban sustainability management: A deep learning perspective Gomede et al [34] Application of Computational Intelligence to Improve Education in Smart Cities. Cramer et al [35] An extensive evaluation of seven machine learning methods for rainfall prediction in weather derivatives You and Yang [36] Urban expansion in 30 megacities of China: categorizing the driving force profiles to inform the urbanization policy Nagy and Simon [37] Survey on traffic prediction in smart cities Belhajem et al [38] Improving Vehicle Localization in a Smart City with Low Cost Sensor Networks and Support Vector Machines Fernández-Ares et al [39] Studying real traffic and mobility scenarios for a Smart City using a new monitoring and tracking system Belhajem et al [40] Improving low cost sensor based vehicle positioning with Machine Learning Gopalakrishnan [41] Deep Learning in Data-Driven Pavement Image Analysis and Automated Distress Detection: A Review Khan et al [42] Smart City and Smart Tourism: A Case of Dubai Idowu et al [43] Applied machine learning: Forecasting heat load in district heating system Bellini et al [44] Wi-Fi based...…”

Rainfall Prediction using Data Mining Techniques: A Systematic Literature Review

“…The researchers in [31] compared the predictive performance of latest and state of the art method named "Markov chain extended with rainfall prediction" with the other widely used machine learning techniques: Support Vector Regression, Genetic Programming, M5 Rules, M5 Model trees, Radial Basis Neural Networks, and k-Nearest Neighbours. Daily rainfall datasets were collected from 42 cities of two continents, with very diverse climatic features.…”