remotesensing-logo

Journal Browser

Journal Browser

GIS and Remote Sensing Application in Food Production and Food Security

A special issue of Remote Sensing (ISSN 2072-4292). This special issue belongs to the section "Remote Sensing in Agriculture and Vegetation".

Deadline for manuscript submissions: closed (31 January 2020) | Viewed by 13016

Special Issue Editors

European Food Safety Authority (EFSA), ALPHA Unit, Plant Health TeamVia Carlo Magno 1A, 43126 Parma, Italy
Interests: sustainable agriculture; soil ecology; soil conservation; plant protection
Special Issues, Collections and Topics in MDPI journals
Co-Founder and Program Director at HOPE—Humanitarian Operations Foundation, Rue Breydel, 34, 1040 Brussels, Belgium
Interests: remote sensing, natural disasters, hyperspectral remote sensing, radiative transfer models, UAV, spatial analysis, vegetation, SAR, image processing
Consultant for International Organizations
Interests: remote sensing; food security; crop mapping; land cover changes

Special Issue Information

Dear Colleagues,

Agriculture and its mission to feed an increasing human population will be challenged by facing a reduced availability of natural resources, such as soil and water. In this scenario, and with the increasing need of multifunctional exploitation of land, the efficiency of agriculture, and more generally of land management practices should be enhanced.

Geospatial sciences play a pivotal role in several innovative activities and processes related to agriculture and food production. It is at the basis of precision agriculture, but generally speaking is extremely important in order to achieve an increased sustainability and efficiency of agricultural systems and food production.

The contribution of Geographic Information Systems and georeferenced data analysis can range from broad strategic modelling at global scale to the application of precision farming at field scale.

Furthermore, the availability of a huge variety of remote sensing products, from the last generation satellites to drones, from aerial photo to hyperspectral sensors, offers the opportunity to apply these techniques to agriculture and food production. There are promising applications of remote sensing in plant pathology, crop physiology, and more generally in soil science and agronomy.

In plant pathology for instance the application of airborne imaging spectroscopy and thermography can reveal X. fastidiosa infection in olive trees before symptoms are visible. 

With this Special Issue, we would inventory the state-of-the-art research that addresses operational methods for identification and monitoring of soil and crop, as well as processes related to food production. The focus is on drones, aerial and satellite-based data indicators, at field, farm, sub-national, national, and global scales. Results of researches using crop biophysical parameter-based crop yield models as well as the integration of crop models with satellite-based inputs are welcome.

Dr. Ciro Gardi
Dr. Angela De Santis
Ms. Laure Boudinaud
Guest Editors

Keywords

  • remote sensing GIS
  • land cover change
  • soil degradation
  • land take
  • food security
  • plant health

Published Papers (1 paper)

Order results
Result details
Select all
Export citation of selected articles as:

Research

17 pages, 4395 KiB  
Article
Potato Yield Prediction Using Machine Learning Techniques and Sentinel 2 Data
by Diego Gómez, Pablo Salvador, Julia Sanz and Jose Luis Casanova
Remote Sens. 2019, 11(15), 1745; https://doi.org/10.3390/rs11151745 - 24 Jul 2019
Cited by 90 | Viewed by 11448
Abstract
Traditional potato growth models evidence certain limitations, such as the cost of obtaining the input data required to run the models, the lack of spatial information in some instances, or the actual quality of input data. In order to address these issues, we [...] Read more.
Traditional potato growth models evidence certain limitations, such as the cost of obtaining the input data required to run the models, the lack of spatial information in some instances, or the actual quality of input data. In order to address these issues, we develop a model to predict potato yield using satellite remote sensing. In an effort to offer a good predictive model that improves the state of the art on potato precision agriculture, we use images from the twin Sentinel 2 satellites (European Space Agency—Copernicus Programme) over three growing seasons, applying different machine learning models. First, we fitted nine machine learning algorithms with various pre-processing scenarios using variables from July, August and September based on the red, red-edge and infra-red bands of the spectrum. Second, we selected the best performing models and evaluated them against independent test data. Finally, we repeated the previous two steps using only variables corresponding to July and August. Our results showed that the feature selection step proved vital during data pre-processing in order to reduce multicollinearity among predictors. The Regression Quantile Lasso model (11.67% Root Mean Square Error, RMSE; R2 = 0.88 and 9.18% Mean Absolute Error, MAE) and Leap Backwards model (10.94% RMSE, R2 = 0.89 and 8.95% MAE) performed better when predictors with a correlation coefficient > 0.5 were removed from the dataset. In contrast, the Support Vector Machine Radial (svmRadial) performed better with no feature selection method (11.7% RMSE, R2 = 0.93 and 8.64% MAE). In addition, we used a random forest model to predict potato yields in Castilla y León (Spain) 1–2 months prior to harvest, and obtained satisfactory results (11.16% RMSE, R2 = 0.89 and 8.71% MAE). These results demonstrate the suitability of our models to predict potato yields in the region studied. Full article
Show Figures

Graphical abstract

Back to TopTop