地下水為台灣淡水資源供給的重要來源，高硝酸鹽氮濃度地下水會威脅人體健康且是地下水質保護關注的議題，預測高濃度硝酸鹽氮地下水發生位置的工作，對於水資源達到保護與發展減緩衝擊的策略。以數據驅動化的機器學習為基礎的人工智慧方法在近年已成功應用於準確地預測地下水硝酸鹽氮污染情勢。本計畫目標為發展結合機器學習與跨部會政府多元資料建立地下水硝酸鹽氮污染潛勢預測模式，機器學習所需的預測變量資料庫包括來自政府跨部會土地利用、水文、土壤型式、水文地質與硝酸鹽氮輸入等資料。資料將分成五組以進行交叉驗證，最後將探討顯著影響硝酸鹽氮濃度的主要預測變量，並依據這些篩選出的主要變量發展減緩硝酸鹽氮污染的有效策略，這些策略可能包括藉由法律規範控制污染、公眾提高社區意識與改變可能導致硝酸鹽氮污染的人為活動。 ;Groundwater is a vital source of the fresh water supplies in Taiwan. Presence of high nitrate nitrogen concentration can pose threat to human health and is already a major concern for groundwater quality protection. Efforts for predicting the locations of high nitrate nitrogen groundwater are required for the protection of water resources and development of mitigation strategies. Most recently, artificial intelligence (AI) techniques like data-driven machine learning approaches have proven their worth for successively and accurately characterizing nitrate nitrogen groundwater pollution occurrence. In this project, we aim to develop groundwater nitrate nitrogen pollution vulnerability prediction model by combining machine learning and inter-ministerial and inter-agency multivariate data. The data set for predictor variables used for machine learning will include land use, hydrological conditions, soil type, hydrogeology and nitrate nitrogen inputs collected from inter-ministerial and inter-agency. Cross validation will be performed to evaluate the prediction performance by dividing the data into five sets. Ultimately, dominant predictors that significantly influence the nitrate nitrogen concentration will be examined and used for the development of effective strategies for minimize nitrate nitrogen groundwater contamination by using the legislation or regulation to control contamination, public education to raise community awareness and change the anthropogenic activity leading to groundwater nitrate nitrogen contamination.
