Academic Journal of Computing & Information Science, 2024, 7(12); doi: 10.25236/AJCIS.2024.071204.
Junxi Li
School of Mathematical Sciences & College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, 518060, China
Accurate PM2.5 concentration forecasting is pivotal for environmental health and sustainable development. This study introduces a machine learning model leveraging the SHAP framework for enhanced interpretability and prediction accuracy. Utilizing 2023 meteorological data from Beijing's Wanshou Xigong meteorological station, we initially explored all characteristics and selected three algorithms, RF, SVR, and LightGBM, to construct machine learning models for PM2.5 concentration prediction. The R2 of each model on the validation set reached 0.9334, 0.9185, and 0.9472. Ultimately, we conducted SHAP framework interpretability analysis on the LightGBM model, removing features with minimal predictive impact. The R2 of the final prediction model reaches 0.9501. This advancement significantly aids in precisely predicting PM2.5 concentration, supporting proactive environmental and health policies.
RF, SVR, LightGBM, SHAP Framework
Junxi Li. Machine learning-based PM concentration prediction and model interpretability analysis. Academic Journal of Computing & Information Science (2024), Vol. 7, Issue 12: 24-35. https://doi.org/10.25236/AJCIS.2024.071204.
[1] Gehrmann S , Dernoncourt F , Li Y ,et al.Comparing Rule-Based and Deep Learning Models for Patient Phenotyping[J]. 2017.DOI:10.48550/arXiv.1703.08705.
[2] Aboonq M S , Alqahtani S A .Leveraging multivariate analysis and adjusted mutual information to improve stroke prediction and interpretability[J].Neurosciences, 2024, 29(3).DOI:10.17712/nsj. 2024.3. 20230100.
[3] Tao C , Jia M , Wang G ,et al.Time-sensitive prediction of NO_(2) concentration in China using an ensemble machine learning model from multi-source data[J].Journal of Environmental Sciences, 2024(3):30-40.DOI:10.1016/j.jes.2023.02.026.
[4] Luo X , Cheng Y , Wu C ,et al.[An interpretable machine learning-based prediction model for risk of death for patients with ischemic stroke in intensive care unit].[J]. Journal of Southern Medical University, 2023, 43 7:, 1241-1247. DOI:10.12122/j.issn.1673-4254.2023.07.21.
[5] Li X , Sun J , Chen X .Machine Learning-Based Prediction of High-Entropy Alloy Hardness: Design and Experimental Validation of Superior Hardness[J].Transactions of the Indian Institute of Metals, 2024, 77(11):3973-3981.DOI:10.1007/s12666-024-03450-5.
[6] Jessica S , Whitney W , Erin H ,et al.Machine learning-based prediction models in medical decision-making in kidney disease: patient, caregiver, and clinician perspectives on trust and appropriate use[J].Journal of the American Medical Informatics Association, 2024.DOI:10.1093/jamia/ocae255.
[7] Pan Y , Zhao D , Zhang X ,et al.Machine learning-Based model for prediction of Narcolepsy Type 1 in Patients with Obstructive Sleep Apnea with Excessive Daytime Sleepiness[J].Nature & Science of Sleep, 2024, 16.DOI:10.2147/NSS.S456903.
[8] Yan W , Shen Y , Chen S ,et al.Viscosity and melting temperature prediction of mold fluxes based on explainable machine learning and SHapley additive exPlanations[J].Journal of Non-Crystalline Solids: A Journal Devoted to Oxide, Halide, Chalcogenide and Metallic Glasses, Amorphous Semiconductors, Non-Crystalline Films, Glass-Ceramics and Glassy Composites, 2024:636.
[9] Shang Z , Chen Y , Lai D ,et al.A novel interpretability machine learning model for wind speed forecasting based on feature and sub-model selection[J].Expert Systems With Applications, 2024, 255.DOI:10.1016/j.eswa.2024.124560.
[10] Liu C , Lu Y , Feng J ,et al.Prediction and customized design of Curie temperature of Fe-based amorphous alloys based on interpretable machine learning[J].Materials Today Communications, 2024, 38.DOI:10.1016/j.mtcomm.2023.107667.