Rosa Viviana Loisi

Agricultural plastic waste spatial estimation by Landsat 8 satellite images

Abstract The use of plastic materials in agriculture involves several benefits but it results in huge quantities of agricultural plastic waste to be disposed of. Input and output data on the use of plastics in agriculture are often difficult to obtain and poor waste management schemes have been developed. The present research aims to estimate and map agricultural plastic waste by using satellite images. Waste was evaluated by means of the indexes relating waste production to crop type and plastic application as defined by the land use map realized by classifying the Landsat 8 image. The image classification was carried out using Support Vector Machines (SVMs), and the accuracy assessment showed that the overall accuracy was 94.54% and the kappa coefficient equal to 0.934. Data on the plastic waste obtained by the satellite land use map were compared with the data obtained by using the institutional land use map; a difference of 1.74% was identified on the overall quantity of waste.

Georeferencing of agricultural plastic waste

The use of plastic materials in agriculture, for greenhouse covering, soil mulching, irrigation pipes, containers and bags, generates a huge amounts of plastic waste that must be properly disposed of. An adequate waste management and disposal system requires the knowledge of the waste generation on the land. This paper presents the results of a research, based on the application of a Geographical Information System, for mapping the waste generation in the municipality of Trinitapoli, Italy. Aim of the research is to identify the points of waste generation and to quantify the waste. A dedicated geo-referenced database with data on the spatial distribution and amount of the plastic wastes was created; waste density ranged from 3.3 kg ha-1yr-1 to 861 kg ha-1yr-1.