de Souza Marlon F, Lamparelli Rubens A C, Oliveira Murilo H S, Nogueira Guilherme P, Bliska Antonio, Franco Telma T
Center for Plasticulture Engineering (CEP), Center for Energy Planing (NIPE), Universidade Estadual de Campinas (UNICAMP), Campinas, 13083896, Brazil.
Chemical Engineering (FEQ), UNICAMP, Campinas, 13083852, Brazil.
Environ Sci Pollut Res Int. 2024 Oct 5. doi: 10.1007/s11356-024-35026-7.
The increasing use of plastics in rural environments has led to concerns about agricultural plastic waste (APW). However, the plasticulture information gap hinders waste management planning and may lead to plastic residue leakage into the environment with consequent microplastic formation. The location and estimated quantity of the APW are crucial for territorial planning and public policies regarding land use and waste management. Agri-plastic remote detection has attracted increased attention but requires a consensus approach, particularly for mapping plastic-mulched farmlands (PMFs) scattered across vast areas. This article tests whether a streamlined time-series approach minimizes PMF confusion with the background using less processing. Based on the literature, we performed a vast assessment of machine learning techniques and investigated the importance of features in mapping tomato PMF. We evaluated pixel-based and object-based classifications in harmonized Sentinel-2 level-2A images, added plastic indices, and compared six classifiers. The best result showed an overall accuracy of 99.7% through pixel-based using the multilayer perceptron (MLP) classifier. The 3-time series with a 30-day composite exhibited increased accuracy, a decrease in background confusion, and was a viable alternative for overcoming the impact of cloud cover on images at certain times of the year in our study area, which leads to a potentially reliable methodology for APW mapping for future studies. To our knowledge, the presented PMF map is the first for Latin America. This represents a first step toward promoting the circularity of all agricultural plastic in the region, minimizing the impacts of degradation on the environment.
塑料在农村环境中的使用日益增加，引发了人们对农业塑料废弃物（APW）的担忧。然而，设施农业信息差距阻碍了废物管理规划，并可能导致塑料残留物泄漏到环境中，进而形成微塑料。APW的位置和估计数量对于土地利用和废物管理的区域规划及公共政策至关重要。农业塑料遥感探测已引起越来越多的关注，但需要一种共识方法，特别是对于绘制分布在广大区域的塑料地膜农田（PMF）而言。本文测试了一种简化的时间序列方法是否能以较少的处理量将PMF与背景的混淆降至最低。基于文献，我们对机器学习技术进行了广泛评估，并研究了特征在绘制番茄PMF中的重要性。我们在统一的哨兵 - 2二级A图像中评估了基于像素和基于对象的分类，添加了塑料指数，并比较了六个分类器。最佳结果显示，使用多层感知器（MLP）分类器通过基于像素的方法总体准确率达到99.7%。30天合成的3个时间序列显示准确率提高，背景混淆减少，并且是克服我们研究区域一年中某些时候云层覆盖对图像影响的可行替代方法，这为未来研究提供了一种潜在可靠的APW绘图方法。据我们所知，所呈现的PMF地图是拉丁美洲的首张此类地图。这代表了朝着促进该地区所有农业塑料的循环利用迈出的第一步，最大限度地减少降解对环境的影响。
