terclim by ICS banner
IVES 9 IVES Conference Series 9 Learning from remote sensing data: a case study in the Trentino region 

Learning from remote sensing data: a case study in the Trentino region 


Recent developments in satellite technology have yielded a substantial volume of data, providing a foundation for various machine learning approaches. These applications, utilizing extensive datasets, offer valuable insights into Earth’s conditions. Examples include climate change analysis, risk and damage assessment, water quality evaluation, and crop monitoring. Our study focuses on exploiting satellite thermal and multispectral imaging, and vegetation indexes, such as NDVI, in conjunction with ground truth information about soil type, land usage (forest, urban, crop cultivation), and irrigation water sources in the Trentino region in North-East of Italy. Trentino, characterized by diverse landscapes ranging from forests to crop fields, is notable for its grapevine cultivation, a significant contributor to the Italian wine industry. Our research aims to analyze the past two decades of satellite data (NASA and Copernicus) using supervised and unsupervised learning methods. The objective is to develop models for soil classification, assessing crop health and growth stage (phenology), and optimizing water management practices, specifically in the context of tree crops (mainly vineyards and apple orchards) in this region. This analytical approach seeks to contribute to a more systematic understanding of the environmental and agricultural dynamics in Trentino, facilitating informed and sustainable land management practices.


Publication date: June 14, 2024

Issue: Open GPB 2024

Type: Poster


Marco Moretto1*, Luca Delucchi1, Roberto Zorer1, Pietro Franceschi1

1 Research and Innovation Centre, Fondazione Edmund Mach, San Michele all’Adige (Trento), Italy

Contact the author*


machine learning, remote sensing, Trentino, soil, water


IVES Conference Series | Open GPB | Open GPB 2024


Related articles…

Effects of soil characteristics on manganese transfer from soil to vine and wine

Aim: In recent times the export of Beaujolais wines has been jeopardised due to a limit of manganese content (Mn) in wine implemented by China (2 mg/L), related to suspicions of potassium permanganate fraud. Nevertheless, soil Mn content may be high in some soil types in Beaujolais. The aim of this study was to improve knowledge of manganese transfer from soil to vine and wine because data on this subject is scarce.


Brettanomyces bruxellensis is considered as the main spoilage yeast in oenology. Its presence in red wine leads to off-flavour due to the production of volatile phenols such as 4-vinylphenol, 4-vinylguaiacol, 4-ethylphenol and 4-ethylguaiacol, whose aromatic notes are unpleasant (e.g. animal, leather, horse or pharmaceutical). Beside wine, B. bruxellensis is commonly isolated from beer, kombucha and bioethanol production, where its role can be described as negative or positive. Recent genomic studies unveiled the existence of various populations.

Improved analysis of isomeric polyphenol dimers using the 4th dimension of trapped ion mobility spectrometry – mass spectrometry

Dehydrodicatechins have recently received attention as oxidation markers especially in grapes and wine. Their analysis mainly uses LC-MS/MS which is able to differentiate them from their natural isomers (dimeric procyanidins), based on specific fragments

Évolutions qualitative et quantitative des flores microbiennes de moûts de pommes à cidre au cours de la fermentation: relations avec le terroir et la composition physico-chimique des fruits

En France, la filière A.O.C. cidricole emploie de plus en plus de levures initialement sélectionnées pour les fermentations des vins. Le risque d’une uniformisation organoleptique ou d’un marquage

Evaluation of Polarized Projective Mapping as a possible tool for attributing South African Chenin blanc dry wine styles

Multiple Factor Analysis (MFA) According to the Chenin blanc Association of South Africa, there are three recognized dry wine styles, Fresh and Fruity (FF), Rich and Ripe Unwooded (RRU), and Rich and Ripe Wooded (RRW), classically attributed with the help of sensory evaluation. One of the “rapid methods” has drawn our attention for the purpose of simplifying and making style attribution for large sample sets, evaluated during different sessions, more robust. Polarized Projective Mapping (PPM) is a hybrid of Projective Mapping (PM) and Polarised Sensory Positioning (PSP). It is a reference-based method in which poles
(references) are used for the evaluation of similarities and dissimilarities between samples.