Assessing the robustness of Random Forests to map land cover with high resolution satellite image time series over large areas

Pelletier, Charlotte; Valero, Silvia; Inglada, Jordi; Champion, Nicolas; Dedieu, Gérard

doi:10.1016/j.rse.2016.10.010

Cited by 486 publications

(359 citation statements)

References 56 publications

Supporting

Mentioning

341

Contrasting

Unclassified

Order By: Relevance

“…RF was chosen because it has produced more accurate mapping results in land cover classification studies compared to other classifiers [52].…”

Section: Random Forest Classificationmentioning

confidence: 99%

“…The critical steps of RF classification are the selection of the number of predictors at each decision tree node split (mtry) and the number of decision trees to run (ntree) [52]. The mtry parameter was set to the square root of the total number of input features within different feature scenarios (see Table 3), and the ntree parameter was set to a relatively high number (set as 1000) for each feature scenarios to allow for convergence of the Out-Of-Bag (OOB) error statistic since values larger than the default (500) are known to have little influence on the overall classification accuracy [34,51,54].…”

Section: Random Forest Classificationmentioning

confidence: 99%

See 1 more Smart Citation

In-Season Crop Mapping with GF-1/WFV Data by Combining Object-Based Image Analysis and Random Forest

Song

Zhou

et al. 2017

Remote Sensing

View full text Add to dashboard Cite

Producing accurate crop maps during the current growing season is essential for effective agricultural monitoring. Substantial efforts have been made to study regional crop distribution from year to year, but less attention is paid to the dynamics of composition and spatial extent of crops within a season. Understanding how crops are distributed at the early developing stages allows for the timely adjustment of crop planting structure as well as agricultural decision making and management. To address this knowledge gap, this study presents an approach integrating object-based image analysis with random forest (RF) for mapping in-season crop types based on multi-temporal GaoFen satellite data with a spatial resolution of 16 meters. A multiresolution local variance strategy was used to create crop objects, and then object-based spectral/textural features and vegetation indices were extracted from those objects. The RF classifier was employed to identify different crop types at four crop growth seasons by integrating available features. The crop classification performance of different seasons was assessed by calculating F-score values. Results show that crop maps derived using seasonal features achieved an overall accuracy of more than 87%. Compared to the use of spectral features, a feature combination of in-season textures and multi-temporal spectral and vegetation indices performs best when classifying crop types. Spectral and temporal information is more important than texture features for crop mapping. However, texture can be essential information when there is insufficient spectral and temporal information (e.g., crop identification in the early spring). These results indicate that an object-based image analysis combined with random forest has considerable potential for in-season crop mapping using high spatial resolution imagery.

show abstract

“…RF was chosen because it has produced more accurate mapping results in land cover classification studies compared to other classifiers [52].…”

Section: Random Forest Classificationmentioning

confidence: 99%

Section: Random Forest Classificationmentioning

confidence: 99%

In-Season Crop Mapping with GF-1/WFV Data by Combining Object-Based Image Analysis and Random Forest

Song

Zhou

et al. 2017

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Biomass is the most common crop parameter indicating the amount of the yield [1]; and together with nitrogen content information, it can be used to determine the need for additional nitrogen fertilization. feature importance order), and it is less sensitive to overfitting and in parameter selection [45][46][47]. In biomass estimation, RF has shown competitive accuracy among other estimation methods applied in forestry [43,48] and in agricultural [32,[49][50][51] applications.…”

Section: Introductionmentioning

confidence: 99%

Estimating Biomass and Nitrogen Amount of Barley and Grass Using UAV and Aircraft Based Spectral and Photogrammetric 3D Features

et al. 2018

View full text Add to dashboard Cite

Abstract:The timely estimation of crop biomass and nitrogen content is a crucial step in various tasks in precision agriculture, for example in fertilization optimization. Remote sensing using drones and aircrafts offers a feasible tool to carry out this task. Our objective was to develop and assess a methodology for crop biomass and nitrogen estimation, integrating spectral and 3D features that can be extracted using airborne miniaturized multispectral, hyperspectral and colour (RGB) cameras. We used the Random Forest (RF) as the estimator, and in addition Simple Linear Regression (SLR) was used to validate the consistency of the RF results. The method was assessed with empirical datasets captured of a barley field and a grass silage trial site using a hyperspectral camera based on the Fabry-Pérot interferometer (FPI) and a regular RGB camera onboard a drone and an aircraft. Agricultural reference measurements included fresh yield (FY), dry matter yield (DMY) and amount of nitrogen. In DMY estimation of barley, the Pearson Correlation Coefficient (PCC) and the normalized Root Mean Square Error (RMSE%) were at best 0.95% and 33.2%, respectively; and in the grass DMY estimation, the best results were 0.79% and 1.9%, respectively. In the nitrogen amount estimations of barley, the PCC and RMSE% were at best 0.97% and 21.6%, respectively. In the biomass estimation, the best results were obtained when integrating hyperspectral and 3D features, but the integration of RGB images and 3D features also provided results that were almost as good. In nitrogen content estimation, the hyperspectral camera gave the best results. We concluded that the integration of spectral and high spatial resolution 3D features and radiometric calibration was necessary to optimize the accuracy.

show abstract

“…As an ensemble classifier, the RF algorithm was robust to the selection of object features and more stable to segmentation scale variation [21,53]. Compared with other state-of-the-art machine learning algorithms, it was more sensitive to training set size and sampling design [54].…”

Section: The Comparison and Selection Of Machine Learning Algorithmsmentioning

confidence: 99%

Artificial Mangrove Species Mapping Using Pléiades-1: An Evaluation of Pixel-Based and Object-Based Classifications with Selected Machine Learning Algorithms

et al. 2018

View full text Add to dashboard Cite

Abstract:In the dwindling natural mangrove today, mangrove reforestation projects are conducted worldwide to prevent further losses. Due to monoculture and the low survival rate of artificial mangroves, it is necessary to pay attention to mapping and monitoring them dynamically. Remote sensing techniques have been widely used to map mangrove forests due to their capacity for large-scale, accurate, efficient, and repetitive monitoring. This study evaluated the capability of a 0.5-m Pléiades-1 in classifying artificial mangrove species using both pixel-based and object-based classification schemes. For comparison, three machine learning algorithms-decision tree (DT), support vector machine (SVM), and random forest (RF)-were used as the classifiers in the pixel-based and object-based classification procedure. The results showed that both the pixel-based and object-based approaches could recognize the major discriminations between the four major artificial mangrove species. However, the object-based method had a better overall accuracy than the pixel-based method on average. For pixel-based image analysis, SVM produced the highest overall accuracy (79.63%); for object-based image analysis, RF could achieve the highest overall accuracy (82.40%), and it was also the best machine learning algorithm for classifying artificial mangroves. The patches produced by object-based image analysis approaches presented a more generalized appearance and could contiguously depict mangrove species communities. When the same machine learning algorithms were compared by McNemar's test, a statistically significant difference in overall classification accuracy between the pixel-based and object-based classifications only existed in the RF algorithm. Regarding species, monoculture and dominant mangrove species Sonneratia apetala group 1 (SA1) as well as partly mixed and regular shape mangrove species Hibiscus tiliaceus (HT) could well be identified. However, for complex and easily-confused mangrove species Sonneratia apetala group 2 (SA2) and other occasionally presented mangroves species (OT), only major distributions could be extracted, with an accuracy of about two-thirds. This study demonstrated that more than 80% of artificial mangroves species distribution could be mapped.

show abstract

Assessing the robustness of Random Forests to map land cover with high resolution satellite image time series over large areas

Cited by 486 publications

References 56 publications

In-Season Crop Mapping with GF-1/WFV Data by Combining Object-Based Image Analysis and Random Forest

In-Season Crop Mapping with GF-1/WFV Data by Combining Object-Based Image Analysis and Random Forest

Estimating Biomass and Nitrogen Amount of Barley and Grass Using UAV and Aircraft Based Spectral and Photogrammetric 3D Features

Artificial Mangrove Species Mapping Using Pléiades-1: An Evaluation of Pixel-Based and Object-Based Classifications with Selected Machine Learning Algorithms

Contact Info

Product

Resources

About