Forest-Type Classification Using Time-Weighted Dynamic Time Warping Analysis in Mountain Areas: A Case Study in Southern China

Cheng, Kai; Wang, Juanle

doi:10.3390/f10111040

Cited by 35 publications

(20 citation statements)

References 63 publications

(93 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The calibrated PlanetScope data were then used to map cropping intensity information using the RF, ET, XGB, and TWDTW algorithms, with XGB being the most accurate and robust method, and TWDTW the least accurate method. Our results are different from the accuracy of TWDTW found in the studies of Belgiu and Csillik [2] and Cheng and Wang [44], where TWDTW produced better accuracy than the RF and SVM methods; although, accuracy results from our TWDTW analysis is still within the range of the accuracy reported in both these studies. However, our study is similar to the study conducted by Dadi [45], which reported higher accuracy from using RF than TWDTW for cropland mapping.…”

Section: Discussioncontrasting

confidence: 99%

Crop Intensity Mapping Using Dynamic Time Warping and Machine Learning from Multi-Temporal PlanetScope Data

Rafif

Kusuma

Saringatin

et al. 2021

Land

View full text Add to dashboard Cite

Crop intensity information describes the productivity and the sustainability of agricultural land. This information can be used to determine which agricultural lands should be prioritized for intensification or protection. Time-series data from remote sensing can be used to derive the crop intensity information; however, this application is limited when using medium to coarse resolution data. This study aims to use 3.7 m-PlanetScope™ Dove constellation data, which provides daily observations, to map crop intensity information for agricultural land in Magelang District, Indonesia. Two-stage histogram matching, before and after the monthly median composites, is used to normalize the PlanetScope data and to generate monthly data to map crop intensity information. Several methods including Time-Weighted Dynamic Time Warping (TWDTW) and the machine-learning algorithms: Random Forest (RF), Extremely Randomized Trees (ET), and Extreme Gradient Boosting (XGB) are employed in this study, and the results are validated using field survey data. Our results show that XGB generated the highest overall accuracy (OA) (95 ± 4%), followed by RF (92 ± 5%), ET (87 ± 6%), and TWDTW (81 ± 8%), for mapping four-classes of cropping intensity, with the near-infrared (NIR) band being the most important variable for identifying cropping intensity. This study demonstrates the potential of PlanetScope data for the production of cropping intensity maps at detailed resolutions.

show abstract

Section: Discussioncontrasting

confidence: 99%

Crop Intensity Mapping Using Dynamic Time Warping and Machine Learning from Multi-Temporal PlanetScope Data

Rafif

Kusuma

Saringatin

et al. 2021

Land

View full text Add to dashboard Cite

show abstract

“…With constellation of two twin-satellites, Sentinel-2 has a very short revisit time, ideally providing land cover observations every 5 days under cloud-free conditions [10]. Such characteristics proved to be very useful when it comes to vegetation monitoring, with many studies specifically aiming at forest monitoring and inventory [11][12][13].…”

Section: Introductionmentioning

confidence: 99%

“…Multiple studies proved that the use of time-series improves the tree species identification compared to using only single date satellite images [12,14,15]. This way, the species phenology can be exploited, but it also induces some new problems, such as increasing the dimensionality of the data and the requirements for more complex algorithms, and longer processing times [16,17].…”

Section: Introductionmentioning

confidence: 99%

Spatio-Temporal Classification Framework for Mapping Woody Vegetation from Multi-Temporal Sentinel-2 Imagery

et al. 2020

View full text Add to dashboard Cite

The inventory of woody vegetation is of great importance for good forest management. Advancements of remote sensing techniques have provided excellent tools for such purposes, reducing the required amount of time and labor, yet with high accuracy and the information richness. Sentinel-2 is one of the relatively new satellite missions, whose 13 spectral bands and short revisit time proved to be very useful when it comes to forest monitoring. In this study, the novel spatio-temporal classification framework for mapping woody vegetation from Sentinel-2 multitemporal data has been proposed. The used framework is based on the probability random forest classification, where temporal information is explicitly defined in the model. Because of this, several predictions are made for each pixel of the study area, which allow for specific spatio-temporal aggregation to be performed. The proposed methodology has been successfully applied for mapping eight potential forest and shrubby vegetation types over the study area of Serbia. Several spatio-temporal aggregation approaches have been tested, divided into two main groups: pixel-based and neighborhood-based. The validation metrics show that determining the most common vegetation type classes in the neighborhood of 5 × 5 pixels provides the best results. The overall accuracy and kappa coefficient obtained from five-fold cross validation of the results are 82.97% and 0.75, respectively. The corresponding producer’s accuracies range from 36.74% to 97.99% and user’s accuracies range from 46.31% to 98.43%. The proposed methodology proved to be applicable for mapping woody vegetation in Serbia and shows a potential to be implemented in other areas as well. Further testing is necessary to confirm such assumptions.

show abstract

“…Pasquarella et al (2018) combined spectral and temporal features obtained from Landsat time series images and were able to extract forest type information for the western portion of Massachusetts [6]. Grabska et al (2019) calculated temporal-spectral features and used them to retrieve information on various forest types, based on Sentinel-2 time series remote sensing images [7], while Cheng and Wang identified temporal patterns of different forest types and then combined them with spectral indexes and bands to identify forest types in Hunan, China, accurately and in detail [8]. Although these studies achieved forest type classification using spectral or temporal features at a local scale, these methods cannot be extended to large-scale forest type mapping owing to the limitations of remote sensing data acquisition, storage, and analysis capabilities [9,10].…”

Section: Introductionmentioning

confidence: 99%

Mapping Forest Types in China with 10 m Resolution Based on Spectral–Spatial–Temporal Features

2021

Self Cite

View full text Add to dashboard Cite

The comprehensive application of spectral, spatial, and temporal (SST) features derived from remote sensing images is a significant technique for classifying and mapping forest types. Facing limitations in the availability of detailed forest type identification processes for large regions, a forest type classification framework based on SST features was developed in this study. The advantages of Sentinel-2 and Landsat series imagery were used to extract SST forest type classification features, using red-edge bands, a gray-level co-occurrence matrix, and harmonic analysis, with the assistance of the Google Earth Engine platform. Considering four representative Chinese geographic regions—middle and high latitudes, complex mountainous areas, cloudy and rainy areas, and the N–S climate transition zone—our method was proven to be effective, with overall classification accuracies > 85%. The scheme to assess the importance of SST features for forest classification in various regions was designed using the Gini criterion in the random forest algorithm and revealed that spectral features were more effective in classifying forest types with complex compositions. Temporal features were found to be favorable for identifying forest types with obvious evergreen and deciduous growth patterns, while spatial features produced better classification results for forest types with different spatial structures, such as needle- or broad-leaved forests. The findings of this study can provide a reference for feature selection in remote sensing forest type classification processes, and identifying forest types in this way could provide support for the accurate and sustainable management of forest resources.

show abstract

Forest-Type Classification Using Time-Weighted Dynamic Time Warping Analysis in Mountain Areas: A Case Study in Southern China

Cited by 35 publications

References 63 publications

Crop Intensity Mapping Using Dynamic Time Warping and Machine Learning from Multi-Temporal PlanetScope Data

Crop Intensity Mapping Using Dynamic Time Warping and Machine Learning from Multi-Temporal PlanetScope Data

Spatio-Temporal Classification Framework for Mapping Woody Vegetation from Multi-Temporal Sentinel-2 Imagery

Mapping Forest Types in China with 10 m Resolution Based on Spectral–Spatial–Temporal Features

Contact Info

Product

Resources

About