Abstract

Forests are among the main places on Earth where carbon is collected and accumulated. However, instrumental assessment of carbon fluxes is possible only for small areas. When solving the scaling problem, machine learning methods are used, which allow transforming the Earth’s surface reflectance intensities in different spectral ranges into ground-based in situ observations. We suggest a regression neural network model of the multilayer perceptron type for assessment of carbon fluxes. The model is trained on FLUXNET network data for a station located in a boreal coniferous forest (56.4615° N, 32.9221° E). Using the vegetation indices NDVI and EVI measured by the MODIS spectroradiometer onboard the Aqua satellite, the air temperature at an altitude of 2 m, and total precipitation as input data, the model estimates the gross primary production (GPP), net ecosystem exchange (NEE), ecosystem respiration (TER), and some other parameters which characterize water and energy fluxes. The statistical assessments for the test dataset show high correlation coefficients (R) and Nash–Sutcliffe coefficients (NSE): R > 0.9 and NSE ≥ 0.87 for GPP and TER; R = 0.4 and NSE = 0.15 for NEE.

中文翻译：

---

利用遥感数据估算森林生态系统碳通量的神经网络模型

摘要

森林是地球上碳收集和积累的主要场所之一。然而，碳通量的仪器评估仅适用于小区域。在解决缩放问题时，使用机器学习方法，将不同光谱范围内的地球表面反射强度转换为地面原位观测。我们建议使用多层感知器类型的回归神经网络模型来评估碳通量。该模型根据位于北方针叶林（北纬 56.4615°，东经 32.9221°）的站点的 FLUXNET 网络数据进行训练。使用Aqua上的 MODIS 光谱辐射计测量的植被指数 NDVI 和 EVI以卫星、海拔2 m处的气温和总降水量作为输入数据，模型估算了总初级生产（GPP）、净生态系统交换（NEE）、生态系统呼吸（TER）以及一些表征水的其他参数和能量通量。测试数据集的统计评估显示出较高的相关系数 ( R ) 和 Nash–Sutcliffe 系数 (NSE)：GPP 和 TER 的R > 0.9 且 NSE ≥ 0.87；对于 NEE， R  = 0.4，NSE = 0.15。