Pre-harvest classification of crop types using a Sentinel-2 time-series and machine learning

Maponya, Mmamokoma Grace; Niekerk, Adriaan van; Mashimbye, Zama Eric

doi:10.1016/j.compag.2019.105164

Cited by 74 publications

(51 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This could be because there was not enough sampling and inventory data to train the SVM and KNN models, as non-parametric methods inevitably require more sample data to obtain higher accuracy [60]. Thus, while Maponya et al [8] and Vafaei et al [75] claimed that the SVM was a great choice for vegetation classification, owing to its ability to handle high dimensional data with less training sample plots, our research confirmed its weakness against the BART model. At the same time, it also proved the ability of non-parametric BART algorithm to handle and model the variables, even with small-sized training datasets, while SVM and KNN underestimated the predictions of the forest characteristics.…”

Section: Discussionmentioning

confidence: 52%

“…The extensive advancements in the remote-sensing (RS) technologies as well as the geographic information system (GIS), computer science, and algorithms, allow not only for a rapid and up-to-date data collection, but also an accurate broad Earth observation and reliable information extraction, specifically related to forest inventory and management [5][6][7]. The Sentinel satellites continuously map and monitor vast forest regions using high spatial, spectral and temporal resolution data, but at low costs [5,8]. The operation of the Sentinel-2 satellite provides multi-spectral data in 13 bands, with a spatial resolution of 10 to 60 m, 10-day revisiting period, and 290 km swath width.…”

Section: Introductionmentioning

confidence: 99%

“…Forest management explicitly necessitates the use of remotely sensed data owing to its cost effectiveness and regional availability. These data has been investigated in terms of data accuracy and reliability in many applications including those of vegetation, agriculture, and forestry [8][9][10]. Therefore, research focus is being increasingly centred on mapping the quantitative distribution of forest stand characteristics (e.g., diameter, height, location, basal area, potential volume of wood, and tree species) as a forest management strategy [1,6].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Comparison of Machine Learning Methods for Mapping the Stand Characteristics of Temperate Forests Using Multi-Spectral Sentinel-2 Data

Ahmadi

Kalantar

Saeidi³

et al. 2020

Remote Sensing

View full text Add to dashboard Cite

The estimation and mapping of forest stand characteristics are vital because this information is necessary for sustainable forest management. The present study considers the use of a Bayesian additive regression trees (BART) algorithm as a non-parametric classifier using Sentinel-2A data and topographic variables to estimate the forest stand characteristics, namely the basal area (m2/ha), stem volume (m3/ha), and stem density (number/ha). These results were compared with those of three other popular machine learning (ML) algorithms, such as generalised linear model (GLM), K-nearest neighbours (KNN), and support vector machine (SVM). A feature selection was done on 28 variables including the multi-spectral bands on Sentinel-2 satellite, related vegetation indices, and ancillary data (elevation, slope, and topographic solar-radiation index derived from digital elevation model (DEM)) and then the most insignificant variables were removed from the datasets by recursive feature elimination (RFE). The study area was a mountainous forest with high biodiversity and an elevation gradient from 26 to 1636 m. An inventory dataset of 1200 sample plots was provided for training and testing the algorithms, and the predictors were fed into the ML models to compute and predict the forest stand characteristics. The accuracies and certainties of the ML models were assessed by their root mean square error (RMSE), mean absolute error (MAE), and R-squared (R2) values. The results demonstrated that BART generated the best basal area and stem volume predictions, followed by GLM, SVM, and KNN. The best RMSE values for both basal area (8.12 m2/ha) and stem volume (29.28 m3/ha) estimation were obtained by BART. Thus, the ability of the BART model for forestry application was established. On the other hand, KNN exhibited the highest RMSE values for all stand variable predictions, thereby exhibiting the least accuracy for this specific application. Moreover, the effectiveness of the narrow Sentinel-2 bands around the red edge and elevation was highlighted for predicting the forest stand characteristics. Therefore, we concluded that the combination of the Sentinel-2 products and topographic variables derived from the PALSAR data used in this study improved the estimation of the forest attributes in temperate forests.

show abstract

Section: Discussionmentioning

confidence: 52%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Comparison of Machine Learning Methods for Mapping the Stand Characteristics of Temperate Forests Using Multi-Spectral Sentinel-2 Data

Ahmadi

Kalantar

Saeidi³

et al. 2020

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Sonobe et al [ 27 ] compared kernel-based extreme learning machine (KELM), multilayer feedforward neural network (FNN), random forest (RF) and support vector machine (SVM) using Sentinel-1A and Sentinel-2A data, and evaluated the sensitivity of the different supervised learning models in the study area of Hokkaido, Japan. Maponya et al [ 28 ] evaluated the classification performance of SVM (support vector machine), DT (decision tree), k-NN (k-nearest neighbor), RF (random forest) and ML (maximum likelihood) for different time series Sentinel-2 data in two different sites in the Western Cape, South Africa, and concluded that SVM and RF can obtain better classification accuracy and greater application potential. In a word, compared with different machine learning classification methods, RF classification method has the characteristics of less parameter setting, stability, maturity and high classification accuracy, so it is suitable for the classification and comparative study of different red edge features in this study.…”

Section: Introductionmentioning

confidence: 99%

Crop Classification Based on Red Edge Features Analysis of GF-6 WFV Data

Kang

Meng

Liu

et al. 2021

Sensors

View full text Add to dashboard Cite

A red edge band is a sensitive spectral band of crops, which helps to improve the accuracy of crop classification. In view of the characteristics of GF-6 WFV data with multiple red edge bands, this paper took Hengshui City, Hebei Province, China, as the study area to carry out red edge feature analysis and crop classification, and analyzed the influence of different red edge features on crop classification. On the basis of GF-6 WFV red edge band spectral analysis, different red edge feature extraction and red edge indices feature importance evaluation, 12 classification schemes were designed based on GF-6 WFV of four bands (only including red, green, blue and near-infrared bands), stepwise discriminant analysis (SDA) and random forest (RF) method were used for feature selection and importance evaluation, and RF classification algorithm was used for crop classification. The results show the following: (1) The red edge 750 band of GF-6 WFV data contains more information content than the red edge 710 band. Compared with the red edge 750 band, the red edge 710 band is more conducive to improving the separability between different crops, which can improve the classification accuracy; (2) According to the classification results of different red edge indices, compared with the SDA method, the RF method is more accurate in the feature importance evaluation; (3) Red edge spectral features, red edge texture features and red edge indices can improve the accuracy of crop classification in different degrees, and the red edge features based on red edge 710 band can improve the accuracy of crop classification more effectively. This study improves the accuracy of remote sensing classification of crops, and can provide reference for the application of GF-6 WFV data and its red edge bands in agricultural remote sensing.

show abstract

“…It is a predictive model that recursively splits a dataset into regions by using a set of binary rules to compute a target value for classification purposes. Multiple decision trees (forming an RF) are created during training, after which the mode of the provided classes of the individual trees sets the output class of the forest [71][72][73][74]. RF requires the adjustment of two parameters, the number of trees which will be created by randomly selecting records from the training samples and the number of variables used for tree nodes.…”

Section: Remote Sensingmentioning

confidence: 99%

A New Model-Based Approach for the Evaluation of the Net Contribution of the European Union Rural Development Program to the Reduction of Water Abstractions in Agriculture

et al. 2020

View full text Add to dashboard Cite

Agriculture is an essential driving force in water resources management and has a central role in the European Union’s Rural Development Programme (RDP). In this study, the solution developed addresses countries characterised by relatively small farms, vast spatial and temporal variability and severe data scarcity. The proposed model-based approach is directly relevant to the evaluation of agricultural policies affecting water abstraction based on multisource data. The evaluation process utilises an entirely spatially distributed, continuous hydrological model. The model provides a gridded output of the main hydrological balance components, as well as vegetation water deficit and irrigation water requirements, on a daily temporal step on a country scale. It provides information at the farm level and facilitates the estimation of water abstractions in agriculture, taking into consideration all the pertinent information included in the Integrated Administration and Control System database that is maintained by RDPs in Europe. Remote sensing data also are used to validate crop patterns. The obtained results were analysed to estimate the net effect of the RDP to the reduction of water abstractions in agriculture. This work produces valuable information concerning the evaluation of agricultural policies and the assessment of land use, and climate change adaptation and mitigation strategies.

show abstract

Pre-harvest classification of crop types using a Sentinel-2 time-series and machine learning

Cited by 74 publications

References 46 publications

Comparison of Machine Learning Methods for Mapping the Stand Characteristics of Temperate Forests Using Multi-Spectral Sentinel-2 Data

Comparison of Machine Learning Methods for Mapping the Stand Characteristics of Temperate Forests Using Multi-Spectral Sentinel-2 Data

Crop Classification Based on Red Edge Features Analysis of GF-6 WFV Data

A New Model-Based Approach for the Evaluation of the Net Contribution of the European Union Rural Development Program to the Reduction of Water Abstractions in Agriculture

Contact Info

Product

Resources

About