Object-based crop classification in Hetao plain using random forest

Artificial terraces are of great importance for agricultural production and soil and water conservation. Automatic high-accuracy mapping of artificial terraces is the basis of monitoring and related studies. Previous research achieved artificial terrace mapping based on high-resolution digital elevation models (DEMs) or imagery. As a result of the importance of the contextual information for terrace mapping, object-based image analysis (OBIA) combined with machine learning (ML) technologies are widely used. However, the selection of an appropriate classifier is of great importance for the terrace mapping task. In this study, the performance of an integrated framework using OBIA and ML for terrace mapping was tested. A catchment, Zhifanggou, in the Loess Plateau, China, was used as the study area. First, optimized image segmentation was conducted. Then, features from the DEMs and imagery were extracted, and the correlations between the features were analyzed and ranked for classification. Finally, three different commonly-used ML classifiers, namely, extreme gradient boosting (XGBoost), random forest (RF), and k-nearest neighbor (KNN), were used for terrace mapping. The comparison with the ground truth, as delineated by field survey, indicated that random forest performed best, with a 95.60% overall accuracy (followed by 94.16% and 92.33% for XGBoost and KNN, respectively). The influence of class imbalance and feature selection is discussed. This work provides a credible framework for mapping artificial terraces.

Download Full-text

Object-based random forest wetland mapping in Conne River, Newfoundland, Canada

Journal of Applied Remote Sensing ◽

10.1117/1.jrs.15.038506 ◽

2021 ◽

Vol 15 (03) ◽

Cited By ~ 1

Author(s):

Jean Elizabeth Granger ◽

Masoud Mahdianpari ◽

Thomas Puestow ◽

Sherry Warren ◽

Fariba Mohammadimanesh ◽

...

Keyword(s):

Random Forest ◽

Wetland Mapping ◽

Object Based

Download Full-text

Early Classification Method for US Corn and Soybean by Incorporating MODIS-Estimated Phenological Data and Historical Classification Maps in Random-Forest Regression Algorithm

Photogrammetric Engineering & Remote Sensing ◽

10.14358/pers.21-00003r2 ◽

2021 ◽

Vol 87 (10) ◽

pp. 747-758

Author(s):

Toshihiro Sakamoto

Keyword(s):

Random Forest ◽

Classification Accuracy ◽

Classification Method ◽

Estimation Accuracy ◽

Random Forest Regression ◽

Crop Phenology ◽

Phenological Data ◽

Mixed Pixel ◽

Crop Classification ◽

Emergence Date

An early crop classification method is functionally required in a near-real-time crop-yield prediction system, especially for upland crops. This study proposes methods to estimate the mixed-pixel ratio of corn, soybean, and other classes within a low-resolution MODIS pixel by coupling MODIS-derived crop phenology information and the past Cropland Data Layer in a random-forest regression algorithm. Verification of the classification accuracy was conducted for the Midwestern United States. The following conclusions are drawn: The use of the random-forest algorithm is effective in estimating the mixed-pixel ratio, which leads to stable classification accuracy; the fusion of historical data and MODIS-derived crop phenology information provides much better crop classification accuracy than when these are used individually; and the input of a longer MODIS data period can improve classification accuracy, especially after day of year 279, because of improved estimation accuracy for the soybean emergence date.

Download Full-text

In-season crop classification using optical remote sensing with random forest over irrigated agricultural fields in Australia

10.5194/egusphere-egu21-4987 ◽

2021 ◽

Author(s):

Zitian Gao ◽

Danlu Guo ◽

Dongryeol Ryu ◽

Andrew Western

Keyword(s):

Random Forest ◽

Water Use ◽

Landsat 8 ◽

Irrigation Season ◽

Yield Estimation ◽

Cropping Season ◽

Crop Type ◽

Eastern Australia ◽

Crop Classification ◽

Type Classification

<p>Timely classification of crop types is critical for agronomic planning in water use and crop production. However, crop type mapping is typically undertaken only after the cropping season, which precludes its uses in later-season water use planning and yield estimation. This study aims 1) to understand how the accuracy of crop type classification changes within cropping season and 2) to suggest the earliest time that it is possible to achieve reliable crop classification. We focused on three main summer crops (corn/maize, cotton and rice) in the Coleambally Irrigation Area (CIA), a major irrigation district in south-eastern Australia consisting of over 4000 fields, for the period of 2013 to 2019. The summer irrigation season in the CIA is from mid-August to mid-May and most farms use surface irrigation to support the growth of summer crops. We developed models that combine satellite data and farmer-reported information for in-season crop type classification. Monthly-averaged Landsat spectral bands were used as input to Random Forest algorithm. We developed multiple models trained with data initially available at the start of the cropping season, then later using all the antecedent images up to different stages within the season. We evaluated the model performance and uncertainty using a two-fold cross validation by randomly choosing training vs. validation periods. Results show that the classification accuracy increases rapidly during the first three months followed by a marginal improvement afterwards. Crops can be classified with a User&#8217;s accuracy above 70% based on the first 2-3 months after the start of the season. Cotton and rice have higher in-season accuracy than corn/maize. The resulting crop maps can be used to support activities such as later-season system scale irrigation decision-making or yield estimation at a regional scale.</p><p>Keywords: Landsat 8 OLI, in-season, multi-year, crop type, Random Forest</p>

Download Full-text

Discriminating Pennisetum alopecuoides plants in a grazed pasture from unmanned aerial vehicles using object‐based image analysis and random forest classifier

Grassland Science ◽

10.1111/grs.12288 ◽

2020 ◽

Cited By ~ 1

Author(s):

Norio Yuba ◽

Kensuke Kawamura ◽

Taisuke Yasuda ◽

Jihyun Lim ◽

Rena Yoshitoshi ◽

...

Keyword(s):

Image Analysis ◽

Random Forest ◽

Unmanned Aerial Vehicles ◽

Random Forest Classifier ◽

Object Based Image Analysis ◽

Grazed Pasture ◽

Aerial Vehicles ◽

Object Based

Download Full-text

Optimal Segmentation Scale Parameter, Feature Subset and Classification Algorithm for Geographic Object-Based Crop Recognition Using Multisource Satellite Imagery

Remote Sensing ◽

10.3390/rs11050514 ◽

2019 ◽

Vol 11 (5) ◽

pp. 514 ◽

Cited By ~ 7

Author(s):

Lingbo Yang ◽

Lamin Mansaray ◽

Jingfeng Huang ◽

Limin Wang

Keyword(s):

Satellite Imagery ◽

Scale Parameter ◽

Selection Method ◽

Classification Algorithm ◽

Feature Subset Selection ◽

Computational Time ◽

Feature Subset ◽

Object Based ◽

Geographic Object ◽

Crop Classification

Geographic object-based image analysis (GEOBIA) has been widely used in the remote sensing of agricultural crops. However, issues related to image segmentation, data redundancy and performance of different classification algorithms with GEOBIA have not been properly addressed in previous studies, thereby compromising the accuracy of subsequent thematic products. It is in this regard that the current study investigates the optimal scale parameter (SP) in multi-resolution segmentation, feature subset, and classification algorithm for use in GEOBIA based on multisource satellite imagery. For this purpose, a novel supervised optimal SP selection method was proposed based on information gain ratio, and was then compared with a preexisting unsupervised optimal SP selection method. Additionally, the recursive feature elimination (RFE) and enhanced RFE (EnRFE) algorithms were modified to generate an improved EnRFE (iEnRFE) algorithm, which was then compared with its precursors in the selection of optimal classification features. Based on the above, random forest (RF), gradient boosting decision tree (GBDT) and support vector machine (SVM) were applied to segmented objects for crop classification. The results indicated that the supervised optimal SP selection method is more suitable for application in heterogeneous land cover, whereas the unsupervised method proved more efficient as it does not require reference segmentation objects. The proposed iEnRFE method outperformed the preexisting EnRFE and RFE methods in optimal feature subset selection as it recorded the highest accuracy and less processing time. The RF, GBDT, and SVM algorithms achieved overall classification accuracies of 91.8%, 92.4%, and 90.5%, respectively. GBDT and RF recorded higher classification accuracies and utilized much less computational time than SVM and are, therefore, considered more suitable for crop classification requiring large numbers of image features. These results have shown that the proposed object-based crop classification scheme could provide a valuable reference for relevant applications of GEOBIA in crop recognition using multisource satellite imagery.

Download Full-text

Mid-season Crop Classification Using Dual-, Compact-, and Full-polarization in Preparation for the Radarsat Constellation Mission (RCM)

Remote Sensing ◽

10.3390/rs11131582 ◽

2019 ◽

Vol 11 (13) ◽

pp. 1582 ◽

Cited By ~ 5

Author(s):

Mahdianpari ◽

Mohammadimanesh ◽

McNairn ◽

Davidson ◽

Rezaee ◽

...

Keyword(s):

Variable Importance ◽

Sar Images ◽

Object Based ◽

Multi Temporal ◽

Importance Analysis ◽

Crop Mapping ◽

Crop Classification ◽

Sar Data ◽

Highly Correlated ◽

Marginal Improvement

Despite recent research on the potential of dual- (DP) and full-polarimetry (FP) Synthetic Aperture Radar (SAR) data for crop mapping, the capability of compact polarimetry (CP) SAR data has not yet been thoroughly investigated. This is of particular concern, given the availability of such data from RADARSAT Constellation Mission (RCM) shortly. Previous studies have illustrated potential for accurate crop mapping using DP and FP SAR features, yet what contribution each feature makes to the model accuracy is not well investigated. Accordingly, this study examined the potential of the early- to mid-season (i.e., May to July) RADARSAT-2 SAR images for crop mapping in an agricultural region in Manitoba, Canada. Various classification scenarios were defined based on the extracted features from FP SAR data, as well as simulated DP and CP SAR data at two different noise floors. Both overall and individual class accuracies were compared for multi-temporal, multi-polarization SAR data using the pixel- and object-based random forest (RF) classification schemes. The late July C-band SAR observation was the most useful data for crop mapping, but the accuracy of single-date image classification was insufficient. Polarimetric decomposition features extracted from CP and FP SAR data produced relatively equal or slightly better classification accuracies compared to the SAR backscattering intensity features. The RF variable importance analysis revealed features that were sensitive to depolarization due to the volume scattering are the most important FP and CP SAR data. Synergistic use of all features resulted in a marginal improvement in overall classification accuracies, given that several extracted features were highly correlated. A reduction of highly correlated features based on integrating the Spearman correlation coefficient and the RF variable importance analyses boosted the accuracy of crop classification. In particular, overall accuracies of 88.23%, 82.12%, and 77.35% were achieved using the optimized features of FP, CP, and DP SAR data, respectively, using the object-based RF algorithm.

Download Full-text