1. Applications of satellite platforms and machine learning for mapping and monitoring grasslands and pastures: A systematic and comprehensive review
- Author
-
Daniele Pinna, Andrea Pezzuolo, Alessia Cogato, Cristina Pornaro, Stefano Macolino, and Francesco Marinello
- Subjects
Remote sensing ,Artificial intelligence ,Machine learning ,Grassland ,Pasture ,Agriculture (General) ,S1-972 ,Agricultural industries ,HD9000-9495 - Abstract
Grasslands and pastures are critical ecosystems globally, essential for their agricultural and environmental roles. Extensive research from 2000 to 2022, comprising 504 articles, has explored the integration of remote sensing and statistical modelling for mapping and monitoring grassland and pasture ecosystems. These articles were sourced from the SCOPUS database and analysed using text mining and natural language processing techniques to investigate the evolution of publication trends over the past twenty-two years. The number of publications per year on this topic has grown consistently in the considered period, from 3 in 2000 to 93 in 2022, doubling their weight compared to the total number of Scopus publications. The quantitative analysis of satellite platform utilisation revealed the increasing importance of Sentinel-2, even though MODIS remained the most utilised satellite platform throughout the study period. The increasing availability of big data has helped spread the utilisation of machine learning algorithms, mostly in the last ten years. Among these, random forest appeared to be the most widespread for grassland and pasture studies. Researchers' primary interest in this field centres on the technologies and their applications. This is evidenced by cluster analysis, which reveals a dominant focus on terms related to the 'Instruments' (25.8 %) and 'Parameters' (24.9 %) categories. This analysis aims to outline the progression of research, offering insights that could be useful in forecasting future trends and facilitating stakeholder engagement in this sector.
- Published
- 2024
- Full Text
- View/download PDF