Information Mining from Heterogeneous Data Sources: A Case Study on Drought Predictions
The objective of this study was to develop information mining methodology for drought modeling and predictions using historical records of climate, satellite, environmental, and oceanic data. The classification and regression tree (CART) approach was used for extracting drought episodes at different...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2017-07-01
|
| Series: | Information |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2078-2489/8/3/79 |
| _version_ | 1818935900993748992 |
|---|---|
| author | Getachew B. Demisse Tsegaye Tadesse Solomon Atnafu Shawndra Hill Brian D. Wardlow Yared Bayissa Andualem Shiferaw |
| author_facet | Getachew B. Demisse Tsegaye Tadesse Solomon Atnafu Shawndra Hill Brian D. Wardlow Yared Bayissa Andualem Shiferaw |
| author_sort | Getachew B. Demisse |
| collection | DOAJ |
| description | The objective of this study was to develop information mining methodology for drought modeling and predictions using historical records of climate, satellite, environmental, and oceanic data. The classification and regression tree (CART) approach was used for extracting drought episodes at different time-lag prediction intervals. Using the CART approach, a number of successful model trees were constructed, which can easily be interpreted and used by decision makers in their drought management decisions. The regression rules produced by CART were found to have correlation coefficients from 0.71–0.95 in rules-alone modeling. The accuracies of the models were found to be higher in the instance and rules model (0.77–0.96) compared to the rules-alone model. From the experimental analysis, it was concluded that different combinations of the nearest neighbor and committee models significantly increase the performances of CART drought models. For more robust results from the developed methodology, it is recommended that future research focus on selecting relevant attributes for slow-onset drought episode identification and prediction. |
| first_indexed | 2024-12-20T05:27:31Z |
| format | Article |
| id | doaj.art-1ba4230cf23545ddad7f9cd7778549cf |
| institution | Directory Open Access Journal |
| issn | 2078-2489 |
| language | English |
| last_indexed | 2024-12-20T05:27:31Z |
| publishDate | 2017-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Information |
| spelling | doaj.art-1ba4230cf23545ddad7f9cd7778549cf2022-12-21T19:51:50ZengMDPI AGInformation2078-24892017-07-01837910.3390/info8030079info8030079Information Mining from Heterogeneous Data Sources: A Case Study on Drought PredictionsGetachew B. Demisse0Tsegaye Tadesse1Solomon Atnafu2Shawndra Hill3Brian D. Wardlow4Yared Bayissa5Andualem Shiferaw6National Drought Mitigation Center, School of Natural Resources, University of Nebraska-Lincoln, Hardin Hall, 3310 Holdrege Street, P.O. Box 830988, Lincoln, NE 68583-0988, USANational Drought Mitigation Center, School of Natural Resources, University of Nebraska-Lincoln, Hardin Hall, 3310 Holdrege Street, P.O. Box 830988, Lincoln, NE 68583-0988, USADepartment of Computer Science, Addis Ababa University, P.O. Box 1176, Addis Ababa, EthiopiaThe Wharton School, University of Pennsylvania, Philadelphia, PA 19104, USANational Drought Mitigation Center, School of Natural Resources, University of Nebraska-Lincoln, Hardin Hall, 3310 Holdrege Street, P.O. Box 830988, Lincoln, NE 68583-0988, USANational Drought Mitigation Center, School of Natural Resources, University of Nebraska-Lincoln, Hardin Hall, 3310 Holdrege Street, P.O. Box 830988, Lincoln, NE 68583-0988, USANational Drought Mitigation Center, School of Natural Resources, University of Nebraska-Lincoln, Hardin Hall, 3310 Holdrege Street, P.O. Box 830988, Lincoln, NE 68583-0988, USAThe objective of this study was to develop information mining methodology for drought modeling and predictions using historical records of climate, satellite, environmental, and oceanic data. The classification and regression tree (CART) approach was used for extracting drought episodes at different time-lag prediction intervals. Using the CART approach, a number of successful model trees were constructed, which can easily be interpreted and used by decision makers in their drought management decisions. The regression rules produced by CART were found to have correlation coefficients from 0.71–0.95 in rules-alone modeling. The accuracies of the models were found to be higher in the instance and rules model (0.77–0.96) compared to the rules-alone model. From the experimental analysis, it was concluded that different combinations of the nearest neighbor and committee models significantly increase the performances of CART drought models. For more robust results from the developed methodology, it is recommended that future research focus on selecting relevant attributes for slow-onset drought episode identification and prediction.https://www.mdpi.com/2078-2489/8/3/79CARTdroughtinformation mininginstancesregression treerules |
| spellingShingle | Getachew B. Demisse Tsegaye Tadesse Solomon Atnafu Shawndra Hill Brian D. Wardlow Yared Bayissa Andualem Shiferaw Information Mining from Heterogeneous Data Sources: A Case Study on Drought Predictions Information CART drought information mining instances regression tree rules |
| title | Information Mining from Heterogeneous Data Sources: A Case Study on Drought Predictions |
| title_full | Information Mining from Heterogeneous Data Sources: A Case Study on Drought Predictions |
| title_fullStr | Information Mining from Heterogeneous Data Sources: A Case Study on Drought Predictions |
| title_full_unstemmed | Information Mining from Heterogeneous Data Sources: A Case Study on Drought Predictions |
| title_short | Information Mining from Heterogeneous Data Sources: A Case Study on Drought Predictions |
| title_sort | information mining from heterogeneous data sources a case study on drought predictions |
| topic | CART drought information mining instances regression tree rules |
| url | https://www.mdpi.com/2078-2489/8/3/79 |
| work_keys_str_mv | AT getachewbdemisse informationminingfromheterogeneousdatasourcesacasestudyondroughtpredictions AT tsegayetadesse informationminingfromheterogeneousdatasourcesacasestudyondroughtpredictions AT solomonatnafu informationminingfromheterogeneousdatasourcesacasestudyondroughtpredictions AT shawndrahill informationminingfromheterogeneousdatasourcesacasestudyondroughtpredictions AT briandwardlow informationminingfromheterogeneousdatasourcesacasestudyondroughtpredictions AT yaredbayissa informationminingfromheterogeneousdatasourcesacasestudyondroughtpredictions AT andualemshiferaw informationminingfromheterogeneousdatasourcesacasestudyondroughtpredictions |