為了驗證我們方法的有效性，我們進行了一系列實驗和比較。結果顯示，我們提出的基於圖像修補的方法在PM2.5濃度的預測和補值方面具有潛力。此外，我們的方法利用了僅使用經緯度地理資訊和PM2.5濃度作為輸入特徵的特點，使其在資料需求和計算複雜度方面相對簡化，這項研究的成果有望為空氣污染監測和環境保護提供有價值的參考和指導。;This study aims to predict and interpolate PM2.5 concentrations in Taiwan while distinguishing itself from other approaches. In comparison to traditional methods, we treat PM2.5 concentrations as images and utilize image inpainting techniques for missing value restoration. Additionally, we specifically emphasize the use of only geographical information (latitude and longitude) and PM2.5 concentrations as input features, excluding other meteorological factors.
To achieve this objective, we collected a substantial amount of PM2.5 concentration data and corresponding geographical information (latitude and longitude) from various locations in Taiwan. Firstly, we transformed the PM2.5 concentration data into image representations, where each pixel represents the PM2.5 value at an observation station. Then, using image inpainting techniques, we predicted and filled in the missing values in the target areas based on the surrounding PM2.5 observation station data. This image-based approach allows us to capture spatial proximity and correlations, thereby improving the effectiveness of missing value interpolation. By treating PM2.5 concentrations as images and applying image inpainting techniques, our approach distinguishes itself from traditional methods.
To validate the effectiveness of our method, we conducted a series of experiments and comparisons. The results demonstrate the potential of our proposed image inpainting-based method in predicting and interpolating PM2.5 concentrations. Furthermore, our method′s reliance solely on geographical information (latitude and longitude) and PM2.5 concentrations as input features simplifies data requirements and computational complexity. The outcomes of this research are expected to provide valuable references and guidance for air pollution monitoring and environmental protection.
