Can a multi-model ensemble improve phenology predictions for climate change studies?

Yun, Kyungdahm; Hsiao, Jennifer; Jung, Myung-Pyo; Choi, In-Tae; Glenn, D. Michael; Shim, Kang-Bo; Kim, Sung Hyun

doi:10.1016/j.ecolmodel.2017.08.003

Cited by 31 publications

(15 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…by discussing their outcome as a possible, rather than a predicted, reaction of the ecosystem. In the present state of model development, an ensemble of model simulations seems as a reasonable approach to reduce inherent uncertainty in model estimates and provide weight of evidence (Lenhart et al 2010, Meier et al 2012b, Queiros et al 2016, Yun et al 2017. The behavior of the relatively simple ecosystem models used here, should be compared to potentially more complex behavior and trophic responses of trait-based models, which can include many more groups (or a blending across groups in terms of size-spectrum models) to better understand how changes in topdown forcing may cascade through the plankton community.…”

Section: Discussionmentioning

confidence: 99%

Responses of summer phytoplankton biomass to changes in top-down forcing: Insights from comparative modelling

Maar

Butenschön

Daewel

et al. 2018

Ecological Modelling

View full text Add to dashboard Cite

The present study describes the responses of summer phytoplankton biomass to changes in top-down forcing (expressed as zooplankton mortality) in three ecosystems (the North Sea, the Baltic Sea and the Nordic Seas) across different 3D ecosystem models. In each of the model set-ups, we applied the same changes in the magnitude of mortality (±20%) of the highest trophic zooplankton level (Z1). Model results showed overall dampened responses of phytoplankton relative to Z1 biomass. Phytoplankton responses varied depending on the food web structure and trophic coupling represented in the models.Hence, a priori model assumptions were found to influence cascades and pathways in model estimates and, thus, become highly relevant when examining ecosystem pressures such as fishing and climate change. Especially, the different roles and parameterizations of additional zooplankton groups grazed by Z1, and their importance for the outcome, emphasized the need for better calibration data. Spatial variability was high within each model indicating that physics (hydrodynamics and temperature) and nutrient dynamics also play vital roles for ecosystem responses to top-down effects. In conclusion, the model comparison indicated that changes in top-down forcing in combination with the modelled foodweb structure affect summer phytoplankton biomass and, thereby, indirectly influence water quality of the systems.3

show abstract

Section: Discussionmentioning

confidence: 99%

Responses of summer phytoplankton biomass to changes in top-down forcing: Insights from comparative modelling

Maar

Butenschön

Daewel

et al. 2018

Ecological Modelling

View full text Add to dashboard Cite

show abstract

“…where n is the number of input layer nodes, q is the number of hidden layer nodes, v is the For the forward propagation process, the output of the hidden layer node can be expressed as 17) where n is the number of input layer nodes, q is the number of hidden layer nodes, v ki is the weight between the ith node of the input layer and the kth node of the hidden layer, and f 1 is the activation function of the hidden layer. Similarly, the relationship between the output layer and the hidden layer can be expressed as…”

Section: Mlp Networkmentioning

confidence: 99%

“…For example, YawenXiao et al used artificial neural networks to produce an ensemble of five classification models-support vector machines (SVMs), k-nearest neighbor (kNN), random forests (RFs), decision trees (DTs), and gradient boosting decision trees (GBDTs)-to construct a multi-model ensemble model to predict cancer [16]. Kyungdahm Yun et al explored the impact of a multi-model ensemble on phenology predictions [17]. Jin Xiao et al combined neural networks, SVMs, and genetic programming into a hybrid model to predict energy consumption.…”

Section: Introductionmentioning

confidence: 99%

Short-Term Photovoltaic Power Output Prediction Based on k-Fold Cross-Validation and an Ensemble Model

2019

View full text Add to dashboard Cite

Short-term photovoltaic power forecasting is of great significance for improving the operation of power systems and increasing the penetration of photovoltaic power. To improve the accuracy of short-term photovoltaic power forecasting, an ensemble-model-based short-term photovoltaic power prediction method is proposed. Firstly, the quartile method is used to process raw data, and the Pearson coefficient method is utilized to assess multiple features affecting the short-term photovoltaic power output. Secondly, the structure of the ensemble model is constructed, and a k-fold cross-validation method is used to train the submodels. The prediction results of each submodel are merged. Finally, the validity of the proposed approach is verified using an actual data set from State Power Investment Corporation Limited. The simulation results show that the quartile method can find outliers which contributes to processing the raw data and improving the accuracy of the model. The k-fold cross-validation method can effectively improve the generalization ability of the model, and the ensemble model can achieve higher prediction accuracy than a single model.

show abstract

“…Changes in climate have already impacted the physiology, phenology, behavior, distribution, and reproduction of many species [ 1 – 3 ]. Species that are expected to be most vulnerable are those that are heavily reliant on environmental temperature for their life history traits and/or those that exhibit temperature-dependent sex determination (TSD) [ 4 – 7 ].…”

Section: Introductionmentioning

confidence: 99%

Warmer and wetter conditions will reduce offspring production of hawksbill turtles in Brazil under climate change

et al. 2018

View full text Add to dashboard Cite

Climate change is expected to impact animals that are heavily reliant on environmental factors, such as sea turtles, since the incubation of their eggs, hatching success and sex ratio are influenced by the environment in which eggs incubate. As climate change progresses it is therefore important to understand how climatic conditions influence their reproductive output and the ramifications to population stability. Here, we examined the influences of five climatic variables (air temperature, accumulated and average precipitation, humidity, solar radiation, and wind speed) at different temporal scales on hawksbill sea turtle (Eretmochelys imbricata) hatchling production at ten nesting beaches within two regions of Brazil (five nesting beaches in Rio Grande do Norte and five in Bahia). Air temperature and accumulated precipitation were the main climatic drivers of hawksbill hatching success (number of eggs hatched within a nest) across Brazil and in Rio Grande do Norte, while air temperature and average precipitation were the main climatic drivers of hatching success at Bahia. Solar radiation was the main climatic driver of emergence success (number of hatchlings that emerged from total hatched eggs within a nest) at both regions. Warmer temperatures and higher solar radiation had negative effects on hatchling production, while wetter conditions had a positive effect. Conservative and extreme climate scenarios show air temperatures are projected to increase at this site, while precipitation projections vary between scenarios and regions throughout the 21st century. We predicted hatching success of undisturbed nests (no recorded depredation or storm-related impacts) will decrease in Brazil by 2100 as a result of how this population is influenced by local climate. This study shows the determining effects of different climate variables and their combinations on an important and critically endangered marine species.

show abstract

Can a multi-model ensemble improve phenology predictions for climate change studies?

Cited by 31 publications

References 61 publications

Responses of summer phytoplankton biomass to changes in top-down forcing: Insights from comparative modelling

Responses of summer phytoplankton biomass to changes in top-down forcing: Insights from comparative modelling

Short-Term Photovoltaic Power Output Prediction Based on k-Fold Cross-Validation and an Ensemble Model

Warmer and wetter conditions will reduce offspring production of hawksbill turtles in Brazil under climate change

Contact Info

Product

Resources

About