Urban Ecosystem Services (UES) Assessment within a 3D Virtual Environment: A Methodological Approach for the Larger Urban Zones (LUZ) of Naples, Italy

Implementing a GIS-Based Digital Atlas of Agricultural Plastics to Reduce Their Environmental Footprint; Part I: A Deductive Approach

The agricultural sector has benefitted over the last century from several factors that have led to an exponential increase in its productive efficiency. The increasing use of new materials, such as plastics, has been one of the most important factors, as they have allowed for increased production in a simpler and more economical way. Various polymer types are used in different phases of the agricultural production cycle, but when their use is incorrectly managed, it can lead to different environmental impacts. In this study, an applied and simplified methodology to manage agricultural plastics monitoring and planning is proposed. The techniques used are based on quantification through the use of different datasets (orthophotos and satellite images) of the areas covered by plastics used for crop protection. The study area chosen is a part of the Ionian Coast of Southern Italy, which includes the most important municipalities of the Basilicata Region for fruit and vegetable production. The use of geographical techniques and observation methodologies, developed in an open-source GIS environment, enabled accurate location of about 2000 hectares of agricultural land covered by plastics, as well as identification of the areas most susceptible to the accumulation of plastic waste. The techniques and the model implemented, due to its simplicity of use and reliability, can be applied by different local authorities in order to realize an Atlas of agricultural plastics, which would be applied for continuous monitoring, thereby enabling the upscaling of future social and ecological impact assessments, identification of new policy impacts, market searches, etc.

Hyperspectral Image Classification Based on Superpixel Pooling Convolutional Neural Network with Transfer Learning

Deep learning-based hyperspectral image (HSI) classification has attracted more and more attention because of its excellent classification ability. Generally, the outstanding performance of these methods mainly depends on a large number of labeled samples. Therefore, it still remains an ongoing challenge how to integrate spatial structure information into these frameworks to classify the HSI with limited training samples. In this study, an effective spectral-spatial HSI classification scheme is proposed based on superpixel pooling convolutional neural network with transfer learning (SP-CNN). The suggested method includes three stages. The first part consists of convolution and pooling operation, which is a down-sampling process to extract the main spectral features of an HSI. The second part is composed of up-sampling and superpixel (homogeneous regions with adaptive shape and size) pooling to explore the spatial structure information of an HSI. Finally, the hyperspectral data with each superpixel as a basic input rather than a pixel are fed to fully connected neural network. In this method, the spectral and spatial information is effectively fused by using superpixel pooling technique. The use of popular transfer learning technology in the proposed classification framework significantly improves the training efficiency of SP-CNN. To evaluate the effectiveness of the SP-CNN, extensive experiments were conducted on three common real HSI datasets acquired from different sensors. With 30 labeled pixels per class, the overall classification accuracy provided by this method on three benchmarks all exceeded 93%, which was at least 4.55% higher than that of several state-of-the-art approaches. Experimental and comparative results prove that the proposed algorithm can effectively classify the HSI with limited training labels.