Prediction of Yield Productivity Zones from Landsat 8 and Sentinel-2A/B and Their Evaluation Using Farm Machinery Measurements

Řezník, Tomáš; Pavelka, Tomáš; Heřman, Lukáš; Lukas, Vojtěch; Širůček, Petr; Leitgeb, Šimon; Leitner, Filip

doi:10.3390/rs12121917

Cited by 25 publications

(10 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sentinel-2 data are understood as the most detailed open-access satellite data suitable for LULC derivations with global coverage. Sentinel-2 data are being used for many different purposes, such as forest monitoring, agriculture, natural hazards monitoring, urban development, local climatology, and hydrological regime observation, i.e., [19][20][21][22][23][24][25].…”

Section: Related Researchmentioning

confidence: 99%

Machine Learning-Based Processing Proof-of-Concept Pipeline for Semi-Automatic Sentinel-2 Imagery Download, Cloudiness Filtering, Classifications, and Updates of Open Land Use/Land Cover Datasets

Řezník

Chytrý

Trojanová

2021

IJGI

Self Cite

View full text Add to dashboard Cite

Land use and land cover are continuously changing in today’s world. Both domains, therefore, have to rely on updates of external information sources from which the relevant land use/land cover (classification) is extracted. Satellite images are frequent candidates due to their temporal and spatial resolution. On the contrary, the extraction of relevant land use/land cover information is demanding in terms of knowledge base and time. The presented approach offers a proof-of-concept machine-learning pipeline that takes care of the entire complex process in the following manner. The relevant Sentinel-2 images are obtained through the pipeline. Later, cloud masking is performed, including the linear interpolation of merged-feature time frames. Subsequently, four-dimensional arrays are created with all potential training data to become a basis for estimators from the scikit-learn library; the LightGBM estimator is then used. Finally, the classified content is applied to the open land use and open land cover databases. The verification of the provided experiment was conducted against detailed cadastral data, to which Shannon’s entropy was applied since the number of cadaster information classes was naturally consistent. The experiment showed a good overall accuracy (OA) of 85.9%. It yielded a classified land use/land cover map of the study area consisting of 7188 km2 in the southern part of the South Moravian Region in the Czech Republic. The developed proof-of-concept machine-learning pipeline is replicable to any other area of interest so far as the requirements for input data are met.

show abstract

Section: Related Researchmentioning

confidence: 99%

Machine Learning-Based Processing Proof-of-Concept Pipeline for Semi-Automatic Sentinel-2 Imagery Download, Cloudiness Filtering, Classifications, and Updates of Open Land Use/Land Cover Datasets

Řezník

Chytrý

Trojanová

2021

IJGI

Self Cite

View full text Add to dashboard Cite

show abstract

“…In this case, fertilization is based on the requirements to cover the nutrient uptake for the expected yield. Yield levels are defined from yield production zones based on the analysis of a time series of yield maps or the trend of distribution of vegetation status from EO data (both 5-10 years) [9]. Production zones represent the percentage deviation from the average yield value on a given field, which is later determined in absolute values of the yield by multiplying with average expected yield values per each field.…”

Section: ) Diagnosis Of the Nitrogen Status In Crops By Continuous Monitoring Of Crop Stands During Vegetationmentioning

confidence: 99%

Delineation of Management Zones Using Satellite Imageries

Charvát

Lukas

Horáková

2021

Big Data in Bioeconomy

Self Cite

View full text Add to dashboard Cite

The chapter describes the development of a platform for mapping crop status and long-time trends by using EO data as a support tool for fertilizing and crop protection. The main focus of the pilot is to monitor cereal fields by high-resolution satellite imagery data (Landsat 8, Sentinel 2) and delineation of management zones within the fields for variable rate application of fertilizers. The first part of the paper is focused on analysis of strategies for recommendations derived from satellite data. The second part is focused on development of a software application with the goal to offer farmers a GIS portal. Here, users can monitor their fields from EO data, based on the specified period and select cloudless scenesfor further analysis. The tool supports collaborative communication between farmers and advisors.

show abstract

“…These empirical models have spatial and temporal constraints for application in another field or season [24,25]. Research to advance the spatial and temporal constraints of empirical models have focused on predicting yield in productivity zones [26] and integrating empirical models with crop modeling [27].…”

Section: Introductionmentioning

confidence: 99%

Training Machine Learning Algorithms Using Remote Sensing and Topographic Indices for Corn Yield Prediction

et al. 2022

View full text Add to dashboard Cite

Methods using remote sensing associated with artificial intelligence to forecast corn yield at the management zone level can help farmers understand the spatial variability of yield before harvesting. Here, spectral bands, topographic wetness index, and topographic position index were integrated to predict corn yield at the management zone using machine learning approaches (e.g., extremely randomized trees, gradient boosting machine, XGBoost algorithms, and stacked ensemble models). We tested four approaches: only spectral bands, spectral bands + topographic position index, spectral bands + topographic wetness index, and spectral bands + topographic position index + topographic wetness index. We also explored two approaches for model calibration: the whole-field approach and the site-specific model at the management zone level. The model’s performance was evaluated in terms of accuracy (mean absolute error) and tendency (estimated mean error). The results showed that it is possible to predict corn yield with reasonable accuracy using spectral crop information associated with the topographic wetness index and topographic position index during the flowering growth stage. Site-specific models increase the accuracy and reduce the tendency of corn yield forecasting on management zones with high, low, and intermediate yields.

show abstract

Prediction of Yield Productivity Zones from Landsat 8 and Sentinel-2A/B and Their Evaluation Using Farm Machinery Measurements

Cited by 25 publications

References 48 publications

Machine Learning-Based Processing Proof-of-Concept Pipeline for Semi-Automatic Sentinel-2 Imagery Download, Cloudiness Filtering, Classifications, and Updates of Open Land Use/Land Cover Datasets

Machine Learning-Based Processing Proof-of-Concept Pipeline for Semi-Automatic Sentinel-2 Imagery Download, Cloudiness Filtering, Classifications, and Updates of Open Land Use/Land Cover Datasets

Delineation of Management Zones Using Satellite Imageries

Training Machine Learning Algorithms Using Remote Sensing and Topographic Indices for Corn Yield Prediction

Contact Info

Product

Resources

About