Cropland and Yield Mapping with Multi-source Remote Sensing

Dear Colleagues,

Accurate and timely information on cropland distribution and crop yield estimation or in-season forecasting can be used to support government agricultural decision making, assist in agricultural management practices, and optimize resource use. With the rapid development of the radiometric, spatial, temporal, and spectral resolutions of remote sensing technology, the integration of multi-source remote sensing is a good way to enhance the spatial resolution, improve data accuracy, capture a broader range of environmental variables, and enable the comprehensive monitoring and analysis of landscapes at various scales. Therefore, to better understand the challenges and opportunities presented by integrating multi-source remotely sensed observations for agricultural applications (especially for cropland or crop yield mapping), this Special Issue aims to invite original and innovative research on applications of multi-source remote sensing for croplands, the crop yield, and crop-type mapping, or crop parameter retrieval using data assimilation algorithms, machine learning, and deep learning methods, or other state-of-the-art approaches. The research areas may include (but are not limited to) the following:

• Crop yield estimation or forecasting;
• Farmland or crop-type mapping;
• Multi-sensor imagery fusion;
• Spatially explicit crop model development, implementation, and validation;
• Model data assimilation algorithms, systems, and uncertainty;
• Multi-source data for retrieving crop parameters;
• Machine learning or deep learning for agricultural studies.

Dr. Wen Zhuo
Prof. Dr. Shibo Fang
Prof. Dr. Yi Xie
Dr. Xiaochuang Yao
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Remote Sensing is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2700 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• yield mapping
• crop yield estimation or forecasts
• cropland mapping
• crop parameter retrieval
• multi-source imagery
• crop growth model
• Google Earth Engine
• data assimilation
• machine learning
• deep learning

Title: Large-scale maize condition mapping to support agricultural risk management
Authors: Edina Birinyi; Dániel Kristóf; Roland Hollós; Zoltán Barcza; Anikó Kern
Affiliation: ELTE Eötvös Loránd University, Institute of Geography and Earth Sciences, Department of Geophysics and Space Science, Pázmány P. st. 1/A, Budapest H-1117, Hungary
Abstract: Crop condition mapping and yield loss detection are highly relevant scientific fields due to their economic importance. Here we report a new, robust, six-category crop condition mapping methodology based on five vegetation indices (VI) using Sentinel-2 imagery at 10 m spatial resolution. We focused on maize, the most drought-affected crop in the Carpathian Basin, using three selected years of data (2017, 2022, and 2023). Our methodology was validated at two different spatial scales against independent reference data. At the parcel level, we used harvester-derived precision yield data from six maize parcels. The agreement between the yield category maps and those predicted from the crop condition time series by our Random Forest model was 84.56%, while the F1 score was 0.74 with a two-category yield map. Using a six-category yield map, the accuracy decreased to 48.57%, while the F1 score was 0.42. The parcel-level analysis has corroborated the applicability of the method at large scales. Country-level validation was made for the six-category crop condition map against official county-scale census data. The proportion of areas with the best and worst crop condition categories in July explained 64% and 77% of the crop yield variability at the county level, respectively. We found that the inclusion of the year 2022 (associated with a severe drought event) was important as it represented a strong baseline for the scaling. The study's novelty is also supported by the inclusion of damage claims from the Hungarian Agricultural Risk Management System (ARMS). The crop condition map was compared with these claims, with further quantitative analysis confirming the method's applicability. This method offers a cost-effective solution for assessing damage claims and can provide early yield loss estimates using only remote sensing data.

Title: Rice yield prediction modelling on a very fine scale using Sentinel-2 imagery
Authors: Christos Karydas1*, Irene Biavetti2 , Miltiadis Iatrou3, Panos Panagos4 , Spiros Mourelatos1
Affiliation: 1 Ecodevelopment S.A., Filyro P.O. Box 2420, 57010 Thessaloniki, Greece 2 Joint Research Centre of the European Commission, Institute for Environment and Sustainability (JRC/IES) 3 Soil and Water Resources Institute, Hellenic Agricultural Organization DIMITRA, 57001 Thessaloniki, Greece 4 Joint Research Centre of the European Commission, Monitoring Agricultural Resources (JRC/MARS) * Correspondence: [email protected]; Tel.: +30 2310678900 (ext. 21)
Abstract: JRC/MARS has been making predictions on expected crop yields in Europe since 1993, achieving satisfactory accuracies, which though can be improved further in several terms. In this research, a new prediction model for rice yield is developed, based on Sentinel-2 and in-situ data, collected from 1000 hectares in Greece over an 8-year period. The new model uses machine learning for the analysis of a huge data-cube, containing spectral, soil, yield, meteorological, and agronomic records. Innovative points of the model can be considered: a) the fine spatial resolution, which is defined at 5 meters on the ground, b) the incorporation of soil data in the predictive algorithm, and c) the incorporation of recorded meteorological variables throughout the cultivation period. The output is expected to improve prediction accuracy significantly, especially with regard to rice cultivars and soil background.