Interpretable spatio-temporal prediction using Deep Neural Network - Local Interpretable Model-agnostic Explanations: A case study on leptospirosis outbreaks in Malaysia
Leptospirosis is a widespread zoonotic disease with complex spatio-temporal dynamics. This study investigates the use of Deep Neural Network (DNN) in combination with Local Interpretable Model-Agnostic Explanations (LIME) for weekly spatio-temporal predictions of leptospirosis occurrence. The predic...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier Ltd
2025
|
| Online Access: | http://psasir.upm.edu.my/id/eprint/121152/ http://psasir.upm.edu.my/id/eprint/121152/1/121152.pdf |
| _version_ | 1848868306781470720 |
|---|---|
| author | Rahmat, Fariq Zulkafli, Zed Ishak, Asnor Juraiza Abdul Rahman, Ribhan Zafira Tahir, Wardah Ab Rahman, Jamalludin Jayaramu, Veianthan De Stercke, Simon Ibrahim, Salwa Ismail, Muhamad |
| author_facet | Rahmat, Fariq Zulkafli, Zed Ishak, Asnor Juraiza Abdul Rahman, Ribhan Zafira Tahir, Wardah Ab Rahman, Jamalludin Jayaramu, Veianthan De Stercke, Simon Ibrahim, Salwa Ismail, Muhamad |
| author_sort | Rahmat, Fariq |
| building | UPM Institutional Repository |
| collection | Online Access |
| description | Leptospirosis is a widespread zoonotic disease with complex spatio-temporal dynamics. This study investigates the use of Deep Neural Network (DNN) in combination with Local Interpretable Model-Agnostic Explanations (LIME) for weekly spatio-temporal predictions of leptospirosis occurrence. The predictive model integrates hydroclimatic and environmental data to assess its effectiveness in predicting leptospirosis cases and quantifying key input variables in Negeri Sembilan, Malaysia. Using a DNN architecture with hyperparameter tuning via grid search, we developed a globally trained model that achieved an overall prediction accuracy of 70.5% across 214 pixels. We identified acidic soil and a higher presence of rubber plantations as strong predictors of leptospirosis occurrence. Additionally, mean temperature and minimum rainfall emerged as important hydroclimatic contributors. These insights enable public health authorities to proactively identify and prioritize high-risk areas for targeted interventions, improving disease mitigation strategies. Furthermore, the methodology is adaptable to other regions with similar environmental and socio-economic conditions, strengthening early warning systems and enhancing preparedness against future leptospirosis outbreaks. While demonstrated on leptospirosis prediction, the proposed DNN-LIME framework is adaptable to spatio-temporal challenges in diverse domains such as supply chain optimization, urban planning, and industrial risk management. The integration of interpretability via LIME ensures actionable insights for stakeholders beyond public health, bridging the gap between complex models and real-world decision-making. |
| first_indexed | 2025-11-15T14:50:18Z |
| format | Article |
| id | upm-121152 |
| institution | Universiti Putra Malaysia |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-15T14:50:18Z |
| publishDate | 2025 |
| publisher | Elsevier Ltd |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | upm-1211522025-10-28T06:30:49Z http://psasir.upm.edu.my/id/eprint/121152/ Interpretable spatio-temporal prediction using Deep Neural Network - Local Interpretable Model-agnostic Explanations: A case study on leptospirosis outbreaks in Malaysia Rahmat, Fariq Zulkafli, Zed Ishak, Asnor Juraiza Abdul Rahman, Ribhan Zafira Tahir, Wardah Ab Rahman, Jamalludin Jayaramu, Veianthan De Stercke, Simon Ibrahim, Salwa Ismail, Muhamad Leptospirosis is a widespread zoonotic disease with complex spatio-temporal dynamics. This study investigates the use of Deep Neural Network (DNN) in combination with Local Interpretable Model-Agnostic Explanations (LIME) for weekly spatio-temporal predictions of leptospirosis occurrence. The predictive model integrates hydroclimatic and environmental data to assess its effectiveness in predicting leptospirosis cases and quantifying key input variables in Negeri Sembilan, Malaysia. Using a DNN architecture with hyperparameter tuning via grid search, we developed a globally trained model that achieved an overall prediction accuracy of 70.5% across 214 pixels. We identified acidic soil and a higher presence of rubber plantations as strong predictors of leptospirosis occurrence. Additionally, mean temperature and minimum rainfall emerged as important hydroclimatic contributors. These insights enable public health authorities to proactively identify and prioritize high-risk areas for targeted interventions, improving disease mitigation strategies. Furthermore, the methodology is adaptable to other regions with similar environmental and socio-economic conditions, strengthening early warning systems and enhancing preparedness against future leptospirosis outbreaks. While demonstrated on leptospirosis prediction, the proposed DNN-LIME framework is adaptable to spatio-temporal challenges in diverse domains such as supply chain optimization, urban planning, and industrial risk management. The integration of interpretability via LIME ensures actionable insights for stakeholders beyond public health, bridging the gap between complex models and real-world decision-making. Elsevier Ltd 2025 Article NonPeerReviewed text en http://psasir.upm.edu.my/id/eprint/121152/1/121152.pdf Rahmat, Fariq and Zulkafli, Zed and Ishak, Asnor Juraiza and Abdul Rahman, Ribhan Zafira and Tahir, Wardah and Ab Rahman, Jamalludin and Jayaramu, Veianthan and De Stercke, Simon and Ibrahim, Salwa and Ismail, Muhamad (2025) Interpretable spatio-temporal prediction using Deep Neural Network - Local Interpretable Model-agnostic Explanations: A case study on leptospirosis outbreaks in Malaysia. Engineering Applications of Artificial Intelligence, 151 (undefined). art. no. 110665. undefined-undefined. ISSN 0952-1976 https://linkinghub.elsevier.com/retrieve/pii/S0952197625006657 10.1016/j.engappai.2025.110665 |
| spellingShingle | Rahmat, Fariq Zulkafli, Zed Ishak, Asnor Juraiza Abdul Rahman, Ribhan Zafira Tahir, Wardah Ab Rahman, Jamalludin Jayaramu, Veianthan De Stercke, Simon Ibrahim, Salwa Ismail, Muhamad Interpretable spatio-temporal prediction using Deep Neural Network - Local Interpretable Model-agnostic Explanations: A case study on leptospirosis outbreaks in Malaysia |
| title | Interpretable spatio-temporal prediction using Deep Neural Network - Local Interpretable Model-agnostic Explanations: A case study on leptospirosis outbreaks in Malaysia |
| title_full | Interpretable spatio-temporal prediction using Deep Neural Network - Local Interpretable Model-agnostic Explanations: A case study on leptospirosis outbreaks in Malaysia |
| title_fullStr | Interpretable spatio-temporal prediction using Deep Neural Network - Local Interpretable Model-agnostic Explanations: A case study on leptospirosis outbreaks in Malaysia |
| title_full_unstemmed | Interpretable spatio-temporal prediction using Deep Neural Network - Local Interpretable Model-agnostic Explanations: A case study on leptospirosis outbreaks in Malaysia |
| title_short | Interpretable spatio-temporal prediction using Deep Neural Network - Local Interpretable Model-agnostic Explanations: A case study on leptospirosis outbreaks in Malaysia |
| title_sort | interpretable spatio-temporal prediction using deep neural network - local interpretable model-agnostic explanations: a case study on leptospirosis outbreaks in malaysia |
| url | http://psasir.upm.edu.my/id/eprint/121152/ http://psasir.upm.edu.my/id/eprint/121152/ http://psasir.upm.edu.my/id/eprint/121152/ http://psasir.upm.edu.my/id/eprint/121152/1/121152.pdf |