A tale of two "forests": random forest machine learning AIDS tropical forest carbon mapping.
A tale of two "forests": random forest machine learning AIDS tropical forest carbon mapping.
复制标题
DOI：
10.1371/journal.pone.0085993
复制
发表时间：
2014
期刊：
影响因子：
3.7
通讯作者：
Chadwick KD
中科院分区：
文献类型：
--
作者：
Mascaro J;Asner GP;Knapp DE;Kennedy-Bowdoin T;Martin RE;Anderson C;Higgins M;Chadwick KD
为了实施REDD+（减少毁林和退化+）等碳抵消机制，需要准确和空间清晰的热带森林碳储量地图。随机森林机器学习算法可以帮助使用遥感数据的碳测绘应用。然而，随机森林从未被与传统的和潜在的更可靠的技术（如区域分层采样和升级）进行过比较，而且它很少用于空间数据。在这里，我们评估了随机森林在提升基于机载激光雷达（光探测和测距）的碳估计方面的性能，与亚马逊西部1600万公顷重点区域的分层方法相比。我们考虑了随机森林的两次运行，包括空间上下文建模和不包括空间上下文建模，在后一种情况下，x和y位置直接在模型中。在每种情况下，我们留出800万公顷（即，焦点区域的一半）进行验证;随机森林的这种严格测试超出了通常由算法编译的内部验证（即，被称为“袋外”），这证明不足以用于这种空间应用。在北方秘鲁的这个异质区域，具有空间背景的模型是随机森林的最佳预成型运行，并解释了验证区域内59%的基于激光雷达的碳估计值，而分层模型的解释率为37%，没有空间背景的随机森林的解释率为43%。随着解释变异的60%改善，当使用具有空间背景的随机森林时，验证LiDAR样本的RMSE从33提高到26 Mg C ha−1。我们的结果表明，在使用随机森林时应考虑空间背景，这样做可能会大大改进碳储量建模，以缓解气候变化。
Accurate and spatially-explicit maps of tropical forest carbon stocks are needed to implement carbon offset mechanisms such as REDD+ (Reduced Deforestation and Degradation Plus). The Random Forest machine learning algorithm may aid carbon mapping applications using remotely-sensed data. However, Random Forest has never been compared to traditional and potentially more reliable techniques such as regionally stratified sampling and upscaling, and it has rarely been employed with spatial data. Here, we evaluated the performance of Random Forest in upscaling airborne LiDAR (Light Detection and Ranging)-based carbon estimates compared to the stratification approach over a 16-million hectare focal area of the Western Amazon. We considered two runs of Random Forest, both with and without spatial contextual modeling by including—in the latter case—x, and y position directly in the model. In each case, we set aside 8 million hectares (i.e., half of the focal area) for validation; this rigorous test of Random Forest went above and beyond the internal validation normally compiled by the algorithm (i.e., called “out-of-bag”), which proved insufficient for this spatial application. In this heterogeneous region of Northern Peru, the model with spatial context was the best preforming run of Random Forest, and explained 59% of LiDAR-based carbon estimates within the validation area, compared to 37% for stratification or 43% by Random Forest without spatial context. With the 60% improvement in explained variation, RMSE against validation LiDAR samples improved from 33 to 26 Mg C ha−1 when using Random Forest with spatial context. Our results suggest that spatial context should be considered when using Random Forest, and that doing so may result in substantially improved carbon stock modeling for purposes of climate change mitigation.
登录
查看更多内容
影响因子：
1.7
作者：
Asner, Gregory P.;Knapp, David E.;Paez-Acosta, Guayana
通讯作者：
Paez-Acosta, Guayana
影响因子：
2.7
作者：
Asner, Gregory P.;Mascaro, Joseph;van Breugel, Michiel
通讯作者：
van Breugel, Michiel
DOI：
10.1073/pnas.1004875107
发表时间：
2010-09-21
影响因子：
11.1
作者：
Asner, Gregory P.;Powell, George V. N.;Hughes, R. Flint
通讯作者：
Hughes, R. Flint
影响因子：
13.5
作者：
Ene, Liviu Theodor;Naesset, Erik;Nelson, Ross
通讯作者：
Nelson, Ross
DOI：
10.1007/978-1-4419-7390-0_8
发表时间：
2011-01-01
期刊：
PREDICTIVE SPECIES AND HABITAT MODELING IN LANDSCAPE ECOLOOGY: CONCEPTS AND APPLICATIONS
影响因子：
--
作者：
Evans, Jeffrey S.;Murphy, Melanie A.;Cushman, Samuel A.
通讯作者：
Cushman, Samuel A.