Refine
Has Fulltext
- yes (3)
Is part of the Bibliography
- yes (3)
Year of publication
- 2023 (3) (remove)
Document Type
- Doctoral Thesis (3) (remove)
Language
- English (3)
Keywords
- Modellierung (3) (remove)
Environmental issues have emerged especially since humans burned fossil fuels, which led to air pollution and climate change that harm the environment. These issues’ substantial consequences evoked strong efforts towards assessing the state of our environment.
Various environmental machine learning (ML) tasks aid these efforts. These tasks concern environmental data but are common ML tasks otherwise, i.e., datasets are split (training, validatition, test), hyperparameters are optimized on validation data, and test set metrics measure a model’s generalizability. This work focuses on the following environmental ML tasks: Regarding air pollution, land use regression (LUR) estimates air pollutant concentrations at locations where no measurements are available based on measured locations and each location’s land use (e.g., industry, streets). For LUR, this work uses data from London (modeled) and Zurich (measured). Concerning climate change, a common ML task is model output statistics (MOS), where a climate model’s output for a study area is altered to better fit Earth observations and provide more accurate climate data. This work uses the regional climate model (RCM) REMO and Earth observations from the E-OBS dataset for MOS. Another task regarding climate is grain size distribution interpolation where soil properties at locations without measurements are estimated based on the few measured locations. This can provide climate models with soil information, that is important for hydrology. For this task, data from Lower Franconia is used.
Such environmental ML tasks commonly have a number of properties: (i) geospatiality, i.e., their data refers to locations relative to the Earth’s surface. (ii) The environmental variables to estimate or predict are usually continuous. (iii) Data can be imbalanced due to relatively rare extreme events (e.g., extreme precipitation). (iv) Multiple related potential target variables can be available per location, since measurement devices often contain different sensors. (v) Labels are spatially often only sparsely available since conducting measurements at all locations of interest is usually infeasible. These properties present challenges but also opportunities when designing ML methods for such tasks.
In the past, environmental ML tasks have been tackled with conventional ML methods, such as linear regression or random forests (RFs). However, the field of ML has made tremendous leaps beyond these classic models through deep learning (DL). In DL, models use multiple layers of neurons, producing increasingly higher-level feature representations with growing layer depth. DL has made previously infeasible ML tasks feasible, improved the performance for many tasks in comparison to existing ML models significantly, and eliminated the need for manual feature engineering in some domains due to its ability to learn features from raw data. To harness these advantages for environmental domains it is promising to develop novel DL methods for environmental ML tasks.
This thesis presents methods for dealing with special challenges and exploiting opportunities inherent to environmental ML tasks in conjunction with DL. To this end, the proposed methods explore the following techniques: (i) Convolutions as in convolutional neural networks (CNNs) to exploit reoccurring spatial patterns in geospatial data. (ii) Posing the problems as regression tasks to estimate the continuous variables. (iii) Density-based weighting to improve estimation performance for rare and extreme events. (iv) Multi-task learning to make use of multiple related target variables. (v) Semi–supervised learning to cope with label sparsity. Using these techniques, this thesis considers four research questions: (i) Can air pollution be estimated without manual feature engineering? This is answered positively by the introduction of the CNN-based LUR model MapLUR as well as the off-the-shelf LUR solution OpenLUR. (ii) Can colocated pollution data improve spatial air pollution models? Multi-task learning for LUR is developed for this, showing potential for improvements with colocated data. (iii) Can DL models improve the quality of climate model outputs? The proposed DL climate MOS architecture ConvMOS demonstrates this. Additionally, semi-supervised training of multilayer perceptrons (MLPs) for grain size distribution interpolation is presented, which can provide improved input data. (iv) Can DL models be taught to better estimate climate extremes? To this end, density-based weighting for imbalanced regression (DenseLoss) is proposed and applied to the DL architecture ConvMOS, improving climate extremes estimation. These methods show how especially DL techniques can be developed for environmental ML tasks with their special characteristics in mind. This allows for better models than previously possible with conventional ML, leading to more accurate assessment and better understanding of the state of our environment.
Empathy, the act of sharing another person’s affective state, is a ubiquitous driver for helping others and feeling close to them. These experiences are integral parts of human behavior and society. The studies presented in this dissertation aimed to investigate the sustainability and stability of social closeness and prosocial decision-making driven by empathy and other social motives. In this vein, four studies were conducted in which behavioral and neural indicators of empathy sustainability were identified using model-based functional magnetic resonance imaging (fMRI).
Applying reinforcement learning, drift-diffusion modelling (DDM), and fMRI, the first two studies were designed to investigate the formation and sustainability of empathy-related social closeness (study 1) and examined how sustainably empathy led to prosocial behavior (study 2). Using DDM and fMRI, the last two studies investigated how empathy combined with reciprocity, the social norm to return a favor, on the one hand and empathy combined with the motive of outcome maximization on the other hand altered the behavioral and neural social decision process.
The results showed that empathy-related social closeness and prosocial decision tendencies persisted even if empathy was rarely reinforced. The sustainability of these empathy effects was related to recalibration of the empathy-related social closeness learning signal (study 1) and the maintenance of a prosocial decision bias (study 2). The findings of study 3 showed that empathy boosted the processing of reciprocity-based social decisions, but not vice versa. Study 4 revealed that empathy-related decisions were modulated by the motive of outcome maximization, depending on individual differences in state empathy.
Together, the studies strongly support the concept of empathy as a sustainable driver of social closeness and prosocial behavior.
Oral antineoplastic drugs are an important component in the treatment of solid tumour diseases, haematological and immunological malignancies. Oral drug administration is associated with positive features (e.g., non-invasive drug administration, outpatient care with a high level of independence for the patient and reduced costs for the health care system). The systemic exposure after oral intake however is prone to high IIV as it strongly depends on gastrointestinal absorption processes, which are per se characterized by high inter-and intraindividual variability. Disease and patient-specific characteristics (e.g., disease state, concomitant diseases, concomitant medication, patient demographics) may additionally contribute to variability in plasma concentrations between individual patients. In addition, many oral antineoplastic drugs show complex PK, which has not yet been fully investigated and elucidated for all substances. All this may increase the risk of suboptimal plasma exposure (either subtherapeutic or toxic), which may ultimately jeopardise the success of therapy, either through a loss of efficacy or through increased, intolerable adverse drug reactions. TDM can be used to detect suboptimal plasma levels and prevent permanent under- or overexposure. It is essential in the treatment of ACC with mitotane, a substance with unfavourable PK and high IIV. In the current work a HPLC-UV method for the TDM of mitotane using VAMS was developed. A low sample volume (20 µl) of capillary blood was used in the developed method, which facilitates dense sampling e.g., at treatment initiation. However, no reference ranges for measurements from capillary blood are established so far and a simple conversion from capillary concentrations to plasma concentrations was not possible. To date the therapeutic range is established only for plasma concentrations and observed capillary concentrations could not be reliable interpretated.The multi-kinase inhibitor cabozantinib is also used for the treatment of ACC. However, not all PK properties, like the characteristic second peak in the cabozantinib concentration-time profile have been fully understood so far. To gain a mechanistic understanding of the compound, a PBPK model was developed and various theories for modelling the second peak were explored, revealing that EHC of the compound is most plausible. Cabozantinib is mainly metabolized via CYP3A4 and susceptible to DDI with e.g., CYP3A4 inducers. The DDI between cabozantinib and rifampin was investigated with the developed PBPK model and revealed a reduced cabozantinib exposure (AUC) by 77%. Hence, the combination of cabozantinib with strong CYP inducers should be avoided. If this is not possible, co administration should be monitored using TDM. The model was also used to simulate cabozantinib plasma concentrations at different stages of liver injury. This showed a 64% and 50% increase in total exposure for mild and moderate liver injury, respectively.Ruxolitinib is used, among others, for patients with acute and chronic GvHD. These patients often also receive posaconazole for invasive fungal prophylaxis leading to CYP3A4 mediated DDI between both substances. Different dosing recommendations from the FDA and EMA on the use of ruxolitinib in combination with posaconazole complicate clinical use. To simulate the effect of this relevant DDI, two separate PBPK models for ruxolitinib and posaconazole were developed and combined. Predicted ruxolitinib exposure was compared to observed plasma concentrations obtained in GvHD patients. The model simulations showed that the observed ruxolitinib concentrations in these patients were generally higher than the simulated concentrations in healthy individuals, with standard dosing present in both scenarios. According to the developed model, EMA recommended RUX dose reduction seems to be plausible as due to the complexity of the disease and intake of extensive co-medication, RUX plasma concentration can be higher than expected.