2020/03/24 by Saverio De Vito, De Vito, Saverio, Girolamo Di Francia +9
Earth and Planetary Sciences · Environmental Science · #Air Quality Monitoring and Forecasting #Air Quality and Health Impacts #Atmospheric chemistry and aerosols #FOS: Computer and information sciences #FOS: Electrical engineering #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Signal Processing (eess.SP) #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2003.12011
openalex publication_date 2020/03/24 · openalex created_date 2022/07/26 · openalex updated_date 2026/07/28
Air Quality Multi-sensors Systems (AQMS) are IoT devices based on low cost\nchemical microsensors array that recently have showed capable to provide\nrelatively accurate air pollutant quantitative estimations. Their availability\npermits to deploy pervasive Air Quality Monitoring (AQM) networks that will\nsolve the geographical sparseness issue that affect the current network of AQ\nRegulatory Monitoring Systems (AQRMS). Unfortunately their accuracy have shown\nlimited in long term field deployments due to negative influence of several\ntechnological issues including sensors poisoning or ageing, non target gas\ninterference, lack of fabrication repeatability, etc. Seasonal changes in\nprobability distribution of priors, observables and hidden context variables\n(i.e. non observable interferents) challenge field data driven calibration\nmodels which short to mid term performances recently rose to the attention of\nUrban authorithies and monitoring agencies. In this work, we address this non\nstationary framework with adaptive learning strategies in order to prolong the\nvalidity of multisensors calibration models enabling continuous learning.\nRelevant parameters influence in different network and note-to-node\nrecalibration scenario is analyzed. Results are hence useful for pervasive\ndeployment aimed to permanent high resolution AQ mapping in urban scenarios as\nwell as for the use of AQMS as AQRMS backup systems providing data when AQRMS\ndata are unavailable due to faults or scheduled mainteinance.\n