C4.5: programs for machine learning
C4.5: programs for machine learning
Learning decision tree classifiers
ACM Computing Surveys (CSUR)
Data mining: concepts and techniques
Data mining: concepts and techniques
EXPLORE: a novel decision tree classification algorithm
BNCOD'10 Proceedings of the 27th British national conference on Data Security and Security Data
AusDM '12 Proceedings of the Tenth Australasian Data Mining Conference - Volume 134
| Hi-index | 0.00 |
World population is increasing at a fast rate resulting in huge pressure on limited water resources. Just about 3% of the earth's total water is freshwater that can be used for various applications including irrigation. Therefore, an efficient irrigation water management is crucial for the survival of human being. In our study area farmers need to order water based on their requirements. Once a request for water is made it typically takes about 7 days to get it at the farm gate from the upstream. Therefore, farmers need to estimate water requirement for the next 7 days in advance in order to get it at the farm gate on time. Currently there is no reliable tool available to the farmers of our study area for estimating future water requirement accurately. Hence, a water demand forecasting technique is crucial for the efficient use of available water. In this study we first prepare a data set containing information on suitable attributes obtained from three different sources namely meteorological data, remote sensing images and water delivery statements. In order to make the prepared data set useful for demand forecasting and pattern extraction we pre-process the data set using a novel approach based on a combination of irrigation and data mining knowledge. We then apply a decision tree technique to forecast future water requirement. We also develop a web based decision support system for the managers, farmers and researchers in order to access various data including the prediction of possible water requirement in future. We evaluate our pre-processing technique by comparing it with another approach. We also compare our decision tree based prediction technique with a traditional prediction approach. Our experimental results indicate the usefulness of our pre-processing and prediction techniques.