A dynamic hierarchical Bayesian approach for forecasting vegetation condition
<p>Agricultural drought, which occurs due to a significant reduction in the moisture required for vegetation growth, is the most complex amongst all drought categories. The onset of agriculture drought is slow and can occur over vast areas with varying spatial effects, differing in areas with...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Copernicus Publications
2022-08-01
|
| Series: | Natural Hazards and Earth System Sciences |
| Online Access: | https://nhess.copernicus.org/articles/22/2725/2022/nhess-22-2725-2022.pdf |
| _version_ | 1811283619019227136 |
|---|---|
| author | E. E. Salakpi P. D. Hurley P. D. Hurley J. M. Muthoka A. Bowell A. Bowell S. Oliver S. Oliver P. Rowhani |
| author_facet | E. E. Salakpi P. D. Hurley P. D. Hurley J. M. Muthoka A. Bowell A. Bowell S. Oliver S. Oliver P. Rowhani |
| author_sort | E. E. Salakpi |
| collection | DOAJ |
| description | <p>Agricultural drought, which occurs due to a significant reduction in the moisture required for vegetation growth, is the most complex amongst all drought categories. The onset of agriculture drought is slow and can occur over vast areas with varying spatial effects, differing in areas with a particular vegetation land cover or specific agro-ecological sub-regions. These spatial variations imply that monitoring and forecasting agricultural drought require complex models that consider the spatial variations in a given region of interest. Hierarchical Bayesian models are suited for modelling such complex systems. Using partially pooled data with sub-groups that characterise spatial differences, these models can capture the sub-group variation while allowing flexibility and information sharing between these sub-groups. This paper's objective is to improve the accuracy and precision of agricultural drought forecasting in spatially diverse regions with a hierarchical Bayesian model. Results showed that the hierarchical Bayesian model was better at capturing the variability for the different agro-ecological zones and vegetation land covers compared to a regular Bayesian auto-regression distributed lags model. The forecasted vegetation condition and associated drought probabilities were more accurate and precise with the hierarchical Bayesian model at 4- to 10-week lead times. Forecasts from the hierarchical model exhibited higher hit rates with a low probability of false alarms for drought events in semi-arid and arid zones. The hierarchical Bayesian model also showed good transferable forecast skills over counties not included in the training data.</p> |
| first_indexed | 2024-04-13T02:14:54Z |
| format | Article |
| id | doaj.art-6556629f85e7419a9da95e13c670f8cb |
| institution | Directory Open Access Journal |
| issn | 1561-8633 1684-9981 |
| language | English |
| last_indexed | 2024-04-13T02:14:54Z |
| publishDate | 2022-08-01 |
| publisher | Copernicus Publications |
| record_format | Article |
| series | Natural Hazards and Earth System Sciences |
| spelling | doaj.art-6556629f85e7419a9da95e13c670f8cb2022-12-22T03:07:11ZengCopernicus PublicationsNatural Hazards and Earth System Sciences1561-86331684-99812022-08-01222725274910.5194/nhess-22-2725-2022A dynamic hierarchical Bayesian approach for forecasting vegetation conditionE. E. Salakpi0P. D. Hurley1P. D. Hurley2J. M. Muthoka3A. Bowell4A. Bowell5S. Oliver6S. Oliver7P. Rowhani8The Data Intensive Science Centre, Department of Physics and Astronomy, University of Sussex, Brighton BN1 9QH, UKThe Data Intensive Science Centre, Department of Physics and Astronomy, University of Sussex, Brighton BN1 9QH, UKAstronomy Centre, Department of Physics and Astronomy, University of Sussex, Brighton BN1 9QH, UKDepartment of Geography, School of Global Studies, University of Sussex, Brighton BN1 9QJ, UKThe Data Intensive Science Centre, Department of Physics and Astronomy, University of Sussex, Brighton BN1 9QH, UKAstronomy Centre, Department of Physics and Astronomy, University of Sussex, Brighton BN1 9QH, UKThe Data Intensive Science Centre, Department of Physics and Astronomy, University of Sussex, Brighton BN1 9QH, UKAstronomy Centre, Department of Physics and Astronomy, University of Sussex, Brighton BN1 9QH, UKDepartment of Geography, School of Global Studies, University of Sussex, Brighton BN1 9QJ, UK<p>Agricultural drought, which occurs due to a significant reduction in the moisture required for vegetation growth, is the most complex amongst all drought categories. The onset of agriculture drought is slow and can occur over vast areas with varying spatial effects, differing in areas with a particular vegetation land cover or specific agro-ecological sub-regions. These spatial variations imply that monitoring and forecasting agricultural drought require complex models that consider the spatial variations in a given region of interest. Hierarchical Bayesian models are suited for modelling such complex systems. Using partially pooled data with sub-groups that characterise spatial differences, these models can capture the sub-group variation while allowing flexibility and information sharing between these sub-groups. This paper's objective is to improve the accuracy and precision of agricultural drought forecasting in spatially diverse regions with a hierarchical Bayesian model. Results showed that the hierarchical Bayesian model was better at capturing the variability for the different agro-ecological zones and vegetation land covers compared to a regular Bayesian auto-regression distributed lags model. The forecasted vegetation condition and associated drought probabilities were more accurate and precise with the hierarchical Bayesian model at 4- to 10-week lead times. Forecasts from the hierarchical model exhibited higher hit rates with a low probability of false alarms for drought events in semi-arid and arid zones. The hierarchical Bayesian model also showed good transferable forecast skills over counties not included in the training data.</p>https://nhess.copernicus.org/articles/22/2725/2022/nhess-22-2725-2022.pdf |
| spellingShingle | E. E. Salakpi P. D. Hurley P. D. Hurley J. M. Muthoka A. Bowell A. Bowell S. Oliver S. Oliver P. Rowhani A dynamic hierarchical Bayesian approach for forecasting vegetation condition Natural Hazards and Earth System Sciences |
| title | A dynamic hierarchical Bayesian approach for forecasting vegetation condition |
| title_full | A dynamic hierarchical Bayesian approach for forecasting vegetation condition |
| title_fullStr | A dynamic hierarchical Bayesian approach for forecasting vegetation condition |
| title_full_unstemmed | A dynamic hierarchical Bayesian approach for forecasting vegetation condition |
| title_short | A dynamic hierarchical Bayesian approach for forecasting vegetation condition |
| title_sort | dynamic hierarchical bayesian approach for forecasting vegetation condition |
| url | https://nhess.copernicus.org/articles/22/2725/2022/nhess-22-2725-2022.pdf |
| work_keys_str_mv | AT eesalakpi adynamichierarchicalbayesianapproachforforecastingvegetationcondition AT pdhurley adynamichierarchicalbayesianapproachforforecastingvegetationcondition AT pdhurley adynamichierarchicalbayesianapproachforforecastingvegetationcondition AT jmmuthoka adynamichierarchicalbayesianapproachforforecastingvegetationcondition AT abowell adynamichierarchicalbayesianapproachforforecastingvegetationcondition AT abowell adynamichierarchicalbayesianapproachforforecastingvegetationcondition AT soliver adynamichierarchicalbayesianapproachforforecastingvegetationcondition AT soliver adynamichierarchicalbayesianapproachforforecastingvegetationcondition AT prowhani adynamichierarchicalbayesianapproachforforecastingvegetationcondition AT eesalakpi dynamichierarchicalbayesianapproachforforecastingvegetationcondition AT pdhurley dynamichierarchicalbayesianapproachforforecastingvegetationcondition AT pdhurley dynamichierarchicalbayesianapproachforforecastingvegetationcondition AT jmmuthoka dynamichierarchicalbayesianapproachforforecastingvegetationcondition AT abowell dynamichierarchicalbayesianapproachforforecastingvegetationcondition AT abowell dynamichierarchicalbayesianapproachforforecastingvegetationcondition AT soliver dynamichierarchicalbayesianapproachforforecastingvegetationcondition AT soliver dynamichierarchicalbayesianapproachforforecastingvegetationcondition AT prowhani dynamichierarchicalbayesianapproachforforecastingvegetationcondition |