Spatio-Temporal Prediction of the Epidemic Spread of Dangerous Pathogens Using Machine Learning Methods
Real-time identification of the occurrence of dangerous pathogens is of crucial importance for the rapid execution of countermeasures. For this purpose, spatial and temporal predictions of the spread of such pathogens are indispensable. The R package papros developed by the authors offers an environ...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-01-01
|
| Series: | ISPRS International Journal of Geo-Information |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2220-9964/9/1/44 |
| _version_ | 1818560355510517760 |
|---|---|
| author | Wolfgang B. Hamer Tim Birr Joseph-Alexander Verreet Rainer Duttmann Holger Klink |
| author_facet | Wolfgang B. Hamer Tim Birr Joseph-Alexander Verreet Rainer Duttmann Holger Klink |
| author_sort | Wolfgang B. Hamer |
| collection | DOAJ |
| description | Real-time identification of the occurrence of dangerous pathogens is of crucial importance for the rapid execution of countermeasures. For this purpose, spatial and temporal predictions of the spread of such pathogens are indispensable. The R package papros developed by the authors offers an environment in which both spatial and temporal predictions can be made, based on local data using various deterministic, geostatistical regionalisation, and machine learning methods. The approach is presented using the example of a crops infection by fungal pathogens, which can substantially reduce the yield if not treated in good time. The situation is made more difficult by the fact that it is particularly difficult to predict the behaviour of wind-dispersed pathogens, such as powdery mildew (<i>Blumeria graminis</i> f. sp. <i>tritici</i>). To forecast pathogen development and spatial dispersal, a modelling process scheme was developed using the aforementioned R package, which combines regionalisation and machine learning techniques. It enables the prediction of the probability of yield- relevant infestation events for an entire federal state in northern Germany at a daily time scale. To run the models, weather and climate information are required, as is knowledge of the pathogen biology. Once fitted to the pathogen, only weather and climate information are necessary to predict such events, with an overall accuracy of 68% in the case of powdery mildew at a regional scale. Thereby, 91% of the observed powdery mildew events are predicted. |
| first_indexed | 2024-12-14T00:37:27Z |
| format | Article |
| id | doaj.art-47b490abcf174d329721ad8edfdcde3e |
| institution | Directory Open Access Journal |
| issn | 2220-9964 |
| language | English |
| last_indexed | 2024-12-14T00:37:27Z |
| publishDate | 2020-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | ISPRS International Journal of Geo-Information |
| spelling | doaj.art-47b490abcf174d329721ad8edfdcde3e2022-12-21T23:24:33ZengMDPI AGISPRS International Journal of Geo-Information2220-99642020-01-01914410.3390/ijgi9010044ijgi9010044Spatio-Temporal Prediction of the Epidemic Spread of Dangerous Pathogens Using Machine Learning MethodsWolfgang B. Hamer0Tim Birr1Joseph-Alexander Verreet2Rainer Duttmann3Holger Klink4Department of Geography, Physical Geography, Christian-Albrechts-Universität zu Kiel, Ludewig-Meyn-Str. 14, 24118 Kiel, GermanyDepartment of Plant Diseases and Plant Protection, Institute of Phytopathology, Christian-Albrechts-Universität zu Kiel, Hermann-Rodewald-Str. 9, 24118 Kiel, GermanyDepartment of Plant Diseases and Plant Protection, Institute of Phytopathology, Christian-Albrechts-Universität zu Kiel, Hermann-Rodewald-Str. 9, 24118 Kiel, GermanyDepartment of Geography, Physical Geography, Christian-Albrechts-Universität zu Kiel, Ludewig-Meyn-Str. 14, 24118 Kiel, GermanyDepartment of Plant Diseases and Plant Protection, Institute of Phytopathology, Christian-Albrechts-Universität zu Kiel, Hermann-Rodewald-Str. 9, 24118 Kiel, GermanyReal-time identification of the occurrence of dangerous pathogens is of crucial importance for the rapid execution of countermeasures. For this purpose, spatial and temporal predictions of the spread of such pathogens are indispensable. The R package papros developed by the authors offers an environment in which both spatial and temporal predictions can be made, based on local data using various deterministic, geostatistical regionalisation, and machine learning methods. The approach is presented using the example of a crops infection by fungal pathogens, which can substantially reduce the yield if not treated in good time. The situation is made more difficult by the fact that it is particularly difficult to predict the behaviour of wind-dispersed pathogens, such as powdery mildew (<i>Blumeria graminis</i> f. sp. <i>tritici</i>). To forecast pathogen development and spatial dispersal, a modelling process scheme was developed using the aforementioned R package, which combines regionalisation and machine learning techniques. It enables the prediction of the probability of yield- relevant infestation events for an entire federal state in northern Germany at a daily time scale. To run the models, weather and climate information are required, as is knowledge of the pathogen biology. Once fitted to the pathogen, only weather and climate information are necessary to predict such events, with an overall accuracy of 68% in the case of powdery mildew at a regional scale. Thereby, 91% of the observed powdery mildew events are predicted.https://www.mdpi.com/2220-9964/9/1/44machine learningrandom forestinfestation forecastpowdery mildew |
| spellingShingle | Wolfgang B. Hamer Tim Birr Joseph-Alexander Verreet Rainer Duttmann Holger Klink Spatio-Temporal Prediction of the Epidemic Spread of Dangerous Pathogens Using Machine Learning Methods ISPRS International Journal of Geo-Information machine learning random forest infestation forecast powdery mildew |
| title | Spatio-Temporal Prediction of the Epidemic Spread of Dangerous Pathogens Using Machine Learning Methods |
| title_full | Spatio-Temporal Prediction of the Epidemic Spread of Dangerous Pathogens Using Machine Learning Methods |
| title_fullStr | Spatio-Temporal Prediction of the Epidemic Spread of Dangerous Pathogens Using Machine Learning Methods |
| title_full_unstemmed | Spatio-Temporal Prediction of the Epidemic Spread of Dangerous Pathogens Using Machine Learning Methods |
| title_short | Spatio-Temporal Prediction of the Epidemic Spread of Dangerous Pathogens Using Machine Learning Methods |
| title_sort | spatio temporal prediction of the epidemic spread of dangerous pathogens using machine learning methods |
| topic | machine learning random forest infestation forecast powdery mildew |
| url | https://www.mdpi.com/2220-9964/9/1/44 |
| work_keys_str_mv | AT wolfgangbhamer spatiotemporalpredictionoftheepidemicspreadofdangerouspathogensusingmachinelearningmethods AT timbirr spatiotemporalpredictionoftheepidemicspreadofdangerouspathogensusingmachinelearningmethods AT josephalexanderverreet spatiotemporalpredictionoftheepidemicspreadofdangerouspathogensusingmachinelearningmethods AT rainerduttmann spatiotemporalpredictionoftheepidemicspreadofdangerouspathogensusingmachinelearningmethods AT holgerklink spatiotemporalpredictionoftheepidemicspreadofdangerouspathogensusingmachinelearningmethods |