Not-so-random forests: Comparing voting and decision tree ensembles for characterizing partial harvest events
Not-so-random forests: Comparing voting and decision tree ensembles for characterizing partial harvest events
复制标题
非随机森林：比较投票和决策树集合以表征部分收获事件
DOI：
10.1016/j.jag.2023.103561
复制
发表时间：
2023
影响因子：
7.5
通讯作者：
Thompson, Jonathan R.
中科院分区：
文献类型：
--
作者：
Pasquarella, Valerie J.;Morreale, Luca L.;Brown, Christopher F.;Kilbride, John B.;Thompson, Jonathan R.
基于集合的变化检测可以通过组合来自多个数据集的信息来提高地图的准确性。有越来越多的文献调查合奏投入和应用程序的森林干扰检测和绘图。然而，除了随机森林分类器之外，很少有研究评估集成方法，这些方法依赖于具有数百个参数的不可解释的“黑箱”算法。此外，大多数基于整体的干扰图没有利用独立和系统地收集的实地森林清查测量。在这里，我们比较了三种方法，将多光谱陆地卫星时间序列生成的变化检测结果与森林清查测量结果相结合，以绘制年度时间步长的森林采伐事件。我们发现，七参数退化决策树集合的性能至少与在相同LandTrendr分割结果上训练和测试的500树随机森林集合一样好，并且两种监督决策树方法的性能始终优于表现最好的投票方法（多数）。与现有的国家森林干扰数据集的比较表明，显着的准确性，证明了开发本地校准的，特定于过程的干扰数据集，如在本研究中开发的收获事件地图的价值提高。此外，通过使用多日期的森林清查测量，我们能够建立一个下限的30%的断面积去除可检测的收获，提供生物物理背景下，我们的收获事件地图。我们的研究结果表明，应用于多光谱时间分割输出的简单可解释决策树可以与更复杂的机器学习方法一样有效，用于表征从部分清除到清除的森林采伐事件，对森林采伐和其他类型干扰的局部准确映射具有重要意义。
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.
登录
查看更多内容
森林状况的变化：使用时间序列卫星图像表征非标准更替干扰
DOI：
--
发表时间：
2020
期刊：
影响因子：
--
作者：
N. Coops;C. Shang;M. Wulder;Joanne C. White;T. Hermosilla
通讯作者：
T. Hermosilla
影响因子：
2.3
作者：
Belair, Ethan P.;Ducey, Mark J.
通讯作者：
Ducey, Mark J.
将森林采伐遗产、森林类型和更新空间模式纳入更新的森林地图：制图结果比较
影响因子：
3.7
作者：
S. Sader;Kasey Legaard
通讯作者：
Kasey Legaard
森林所有权及其变化对缅因州北部森林采伐率、类型和趋势的影响
影响因子：
3.7
作者：
Suming Jin;S. Sader
通讯作者：
S. Sader
影响因子：
5
作者：
Canham, Charles D.;Rogers, Nicole;Buchholz, Thomas
通讯作者：
Buchholz, Thomas