Not-so-random forests: Comparing voting and decision tree ensembles for characterizing partial harvest events
Ensemble-based change detection can improve map accuracies by combining information from multiple datasets. There is a growing literature investigating ensemble inputs and applications for forest disturbance detection and mapping. However, few studies have evaluated ensemble methods other than Rando...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-12-01
|
| Series: | International Journal of Applied Earth Observations and Geoinformation |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1569843223003850 |
| _version_ | 1797389521216602112 |
|---|---|
| author | Valerie J. Pasquarella Luca L. Morreale Christopher F. Brown John B. Kilbride Jonathan R. Thompson |
| author_facet | Valerie J. Pasquarella Luca L. Morreale Christopher F. Brown John B. Kilbride Jonathan R. Thompson |
| author_sort | Valerie J. Pasquarella |
| collection | DOAJ |
| description | Ensemble-based change detection can improve map accuracies by combining information from multiple datasets. There is a growing literature investigating ensemble inputs and applications for forest disturbance detection and mapping. However, few studies have evaluated ensemble methods other than Random Forest classifiers, which rely on uninterpretable “black box” algorithms with hundreds of parameters. Additionally, most ensemble-based disturbance maps do not utilize independently and systematically collected field-based forest inventory measurements. Here, we compared three approaches for combining change detection results generated from multi-spectral Landsat time series with forest inventory measurements to map forest harvest events at an annual time step. We found that seven-parameter degenerate decision tree ensembles performed at least as well as 500-tree Random Forest ensembles trained and tested on the same LandTrendr segmentation results and both supervised decision tree methods consistently outperformed the top-performing voting approach (majority). Comparisons with an existing national forest disturbance dataset indicated notable improvements in accuracy that demonstrate the value of developing locally calibrated, process-specific disturbance datasets like the harvest event maps developed in this study. Furthermore, by using multi-date forest inventory measurements, we are able to establish a lower bound of 30% basal area removal on detectable harvests, providing biophysical context for our harvest event maps. Our results suggest that simple interpretable decision trees applied to multi-spectral temporal segmentation outputs can be as effective as more complex machine learning approaches for characterizing forest harvest events ranging from partial clearing to clear cuts, with important implications for locally accurate mapping of forest harvests and other types of disturbances. |
| first_indexed | 2024-03-08T22:57:12Z |
| format | Article |
| id | doaj.art-1546a6a918b14f1a8c4bb959fb9d98da |
| institution | Directory Open Access Journal |
| issn | 1569-8432 |
| language | English |
| last_indexed | 2024-03-08T22:57:12Z |
| publishDate | 2023-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | International Journal of Applied Earth Observations and Geoinformation |
| spelling | doaj.art-1546a6a918b14f1a8c4bb959fb9d98da2023-12-16T06:06:28ZengElsevierInternational Journal of Applied Earth Observations and Geoinformation1569-84322023-12-01125103561Not-so-random forests: Comparing voting and decision tree ensembles for characterizing partial harvest eventsValerie J. Pasquarella0Luca L. Morreale1Christopher F. Brown2John B. Kilbride3Jonathan R. Thompson4Department of Earth & Environment, Boston University, 685 Commonwealth Avenue, Boston, MA 02215, USA; Harvard Forest, Harvard University, 324 N Main St, Petersham, MA 01366, USA; Corresponding author.Department of Earth & Environment, Boston University, 685 Commonwealth Avenue, Boston, MA 02215, USA; Harvard Forest, Harvard University, 324 N Main St, Petersham, MA 01366, USAGoogle LLC, 1600 Amphitheatre Pkwy., Mountain View, CA 94043, USACollege of Earth, Ocean, and Atmospheric Sciences, Oregon State University, Corvallis, OR 97331, USAHarvard Forest, Harvard University, 324 N Main St, Petersham, MA 01366, USAEnsemble-based change detection can improve map accuracies by combining information from multiple datasets. There is a growing literature investigating ensemble inputs and applications for forest disturbance detection and mapping. However, few studies have evaluated ensemble methods other than Random Forest classifiers, which rely on uninterpretable “black box” algorithms with hundreds of parameters. Additionally, most ensemble-based disturbance maps do not utilize independently and systematically collected field-based forest inventory measurements. Here, we compared three approaches for combining change detection results generated from multi-spectral Landsat time series with forest inventory measurements to map forest harvest events at an annual time step. We found that seven-parameter degenerate decision tree ensembles performed at least as well as 500-tree Random Forest ensembles trained and tested on the same LandTrendr segmentation results and both supervised decision tree methods consistently outperformed the top-performing voting approach (majority). Comparisons with an existing national forest disturbance dataset indicated notable improvements in accuracy that demonstrate the value of developing locally calibrated, process-specific disturbance datasets like the harvest event maps developed in this study. Furthermore, by using multi-date forest inventory measurements, we are able to establish a lower bound of 30% basal area removal on detectable harvests, providing biophysical context for our harvest event maps. Our results suggest that simple interpretable decision trees applied to multi-spectral temporal segmentation outputs can be as effective as more complex machine learning approaches for characterizing forest harvest events ranging from partial clearing to clear cuts, with important implications for locally accurate mapping of forest harvests and other types of disturbances.http://www.sciencedirect.com/science/article/pii/S1569843223003850Change detectionForest harvestTemporal segmentationLandTrendrForest Inventory and AnalysisEnsemble methods |
| spellingShingle | Valerie J. Pasquarella Luca L. Morreale Christopher F. Brown John B. Kilbride Jonathan R. Thompson Not-so-random forests: Comparing voting and decision tree ensembles for characterizing partial harvest events International Journal of Applied Earth Observations and Geoinformation Change detection Forest harvest Temporal segmentation LandTrendr Forest Inventory and Analysis Ensemble methods |
| title | Not-so-random forests: Comparing voting and decision tree ensembles for characterizing partial harvest events |
| title_full | Not-so-random forests: Comparing voting and decision tree ensembles for characterizing partial harvest events |
| title_fullStr | Not-so-random forests: Comparing voting and decision tree ensembles for characterizing partial harvest events |
| title_full_unstemmed | Not-so-random forests: Comparing voting and decision tree ensembles for characterizing partial harvest events |
| title_short | Not-so-random forests: Comparing voting and decision tree ensembles for characterizing partial harvest events |
| title_sort | not so random forests comparing voting and decision tree ensembles for characterizing partial harvest events |
| topic | Change detection Forest harvest Temporal segmentation LandTrendr Forest Inventory and Analysis Ensemble methods |
| url | http://www.sciencedirect.com/science/article/pii/S1569843223003850 |
| work_keys_str_mv | AT valeriejpasquarella notsorandomforestscomparingvotinganddecisiontreeensemblesforcharacterizingpartialharvestevents AT lucalmorreale notsorandomforestscomparingvotinganddecisiontreeensemblesforcharacterizingpartialharvestevents AT christopherfbrown notsorandomforestscomparingvotinganddecisiontreeensemblesforcharacterizingpartialharvestevents AT johnbkilbride notsorandomforestscomparingvotinganddecisiontreeensemblesforcharacterizingpartialharvestevents AT jonathanrthompson notsorandomforestscomparingvotinganddecisiontreeensemblesforcharacterizingpartialharvestevents |