| 1. |
- He, Liyuan, et al.
(author)
-
Dynamics of Fungal and Bacterial Biomass Carbon in Natural Ecosystems: Site-level Applications of the CLM-Microbe Model
- 2021
-
In: Journal of Advances in Modeling Earth Systems. - 1942-2466. ; 13:2
-
Journal article (peer-reviewed)abstract
- Explicitly representing microbial processes has been recognized as a key improvement to Earth system models for the realistic projections of soil carbon (C) and climate dynamics. The CLM‐Microbe model builds upon the CLM4.5 and explicitly represents two major soil microbial groups, fungi and bacteria. Based on the compiled time‐series data of fungal (FBC) and bacterial (BBC) biomass C from nine biomes, we parameterized and validated the CLM‐Microbe model, and further conducted sensitivity analysis and uncertainty analysis for simulating C cycling. The model performance was evaluated with mean absolute error (MAE), root mean square error (RMSE), and coefficient of determination (R2) for relative change in FBC and BBC. The CLM‐Microbe model is able to reasonably capture the seasonal dynamics of FBC and BBC across biomes, particularly for tropical/subtropical forest, temperate broadleaf forest, and grassland, with MAE < 0.49 for FBC and <0.36 for BBC and RMSE <0.52 FBC and <0.39 for BBC, while R2 values are relatively smaller in some biomes (e.g., shrub) due to small sample sizes. We found good consistencies between simulated and observed FBC (R2=0.70, P<0.001) and BBC (R2=0.26, P<0.05) on average across biomes, but the model is not able to fully capture the large variation in observed FBC and BBC. Sensitivity analysis shows the most critical parameters are turnover rate, carbon‐to‐nitrogen ratio of fungi and bacteria, and microbial assimilation efficiency. This study confirms that the explicit representation of soil microbial mechanisms enhances model performance in simulating C variables such as heterotrophic respiration and soil organic C density. The further application of the CLM‐Microbe model would deepen our understanding of microbial contributions to the global C cycle.
|
|
| 2. |
- Lindgren, Amelie, et al.
(author)
-
Reconstructing Past Global Vegetation With Random Forest Machine Learning, Sacrificing the Dynamic Response for Robust Results
- 2021
-
In: Journal of Advances in Modeling Earth Systems. - 1942-2466. ; 13:2
-
Journal article (peer-reviewed)abstract
- Vegetation is an important component in the Earth system, providing a direct link between the biosphere and atmosphere. As such, a representative vegetation pattern is needed to accurately simulate climate. We attempt to model global vegetation (biomes) with a data‐driven approach, to test if this allows us to create robust global and regional vegetation patterns. This not only provides quantitative reconstructions of past vegetation cover as a climate forcing, but also improves our understanding of past land cover‐climate interactions which have important implications for the future. By using a Random Forest (RF) machine learning tool, we train the vegetation reconstruction with available biomized pollen data of present and past conditions to produce broad‐scale vegetation patterns for the preindustrial (PI), the mid‐Holocene (MH, ∼6,000 years ago), and the Last Glacial Maximum (LGM, ∼21,000 years ago). We test the method's robustness by introducing a systematic temperature bias based on existing climate model spread and compare the result with that of LPJ‐GUESS, an individual‐based dynamic global vegetation model. The results show that the RF approach is able to produce robust patterns for periods and regions well constrained by evidence (the PI and the MH), but fails when evidence is scarce (the LGM). The apparent robustness of this method is achieved at the cost of sacrificing the ability to model dynamic vegetation response to a changing climate.
|
|
| 3. |
- Scher, Sebastian, et al.
(author)
-
Ensemble Methods for Neural Network-Based Weather Forecasts
- 2021
-
In: Journal of Advances in Modeling Earth Systems. - : American Geophysical Union (AGU). - 1942-2466. ; 13:2
-
Journal article (peer-reviewed)abstract
- Ensemble weather forecasts enable a measure of uncertainty to be attached to each forecast, by computing the ensemble's spread. However, generating an ensemble with a good spread-error relationship is far from trivial, and a wide range of approaches to achieve this have been explored-chiefly in the context of numerical weather prediction models. Here, we aim to transform a deterministic neural network weather forecasting system into an ensemble forecasting system. We test four methods to generate the ensemble: random initial perturbations, retraining of the neural network, use of random dropout in the network, and the creation of initial perturbations with singular vector decomposition. The latter method is widely used in numerical weather prediction models, but is yet to be tested on neural networks. The ensemble mean forecasts obtained from these four approaches all beat the unperturbed neural network forecasts, with the retraining method yielding the highest improvement. However, the skill of the neural network forecasts is systematically lower than that of state-of-the-art numerical weather prediction models.
|
|
