Sökning: "DGVM"
Visar resultat 1 - 5 av 11 uppsatser innehållade ordet DGVM.
1. Applying LPJ-GUESS on the Arctic: A model evaluation and benchmarking study
Master-uppsats, Lunds universitet/Institutionen för naturgeografi och ekosystemvetenskapSammanfattning : Warming in the Arctic occurs at a much higher rate than the global average, which has a considerable impact on the Arctic terrestrial carbon cycle. Permafrost thawing can release substantial amounts of carbon, whilst tundra shrubification and tree-line advance, on the other hand, may compensate for this. LÄS MER
2. Evaluating a new hydraulic implementation in LPJ-GUESS for three sites in north Europe
Master-uppsats, Lunds universitet/Institutionen för naturgeografi och ekosystemvetenskapSammanfattning : Drought is projected to increase in frequency and intensity and impacts trees with increased water stress and increased mortality rate. Water stresses can cause hydraulic failure-related mortality or carbon starvation due to tree species having different strategies to deal with water stresses. LÄS MER
3. Evaluating the ability of LPJ-GUESS to simulate the tree size structures of tropical forests
Kandidat-uppsats, Lunds universitet/Institutionen för naturgeografi och ekosystemvetenskapSammanfattning : Tropical forests are of great importance to all living-beings due to their high biodiversity and the valu-able resources, such as food and fuel, they provide. In addition, tropical trees sequester a high amount of carbon and consequently over half of the global forest carbon stock can be found in the tropics. LÄS MER
4. Multitask Convolutional Neural Network Emulators for Global Crop Models - Supervised Deep Learning in Large Hypercubes of Non-IID Data
Master-uppsats, Lunds universitet/Matematisk statistikSammanfattning : The aim of this thesis is to establish whether a neural network (NN) can be used for emulation of simulated global crop production - retrieved from the computationally demanding dynamic global vegetation model (DGVM) Lund-Potsdam-Jena General Ecosystem Simulator (LPJ-GUESS). It has been devoted to elaboration with various types of neural network architectures: Branched NNs capable of processing inputs of mixed data types; Convolutional Neural Network (CNN) architectures able to perform automated temporal feature extraction of the given weather time series; simpler fully connected (FC) structures as well as Multitask NNs. LÄS MER
5. Emulators for dynamic vegetation models - Supervised learning in large data sets
Master-uppsats, Lunds universitet/Matematisk statistikSammanfattning : The observed and expected changes in the environment due to human actions implies risks that future food production will be insufficient. Pre- dicting the impact these changes have on the agricultural system could be beneficial by allowing for proactive mitigating efforts. LÄS MER