In this thesis, a new learning algorithm is introduced that is targeted towards individual fairness. In order to be individually fair, mispredictions need to be avoided as each such prediction means the learning algorithm was unfair towards some individual. Therefore, achieving individual fairness implies having a perfect classifier, which is...
In this work, we study the problem of learning and improving policies for probabilistic planning problems. In the first part, we train neural network policies for probabilistic planning problems modeled as factored Markov decision problems. The objective is to train problem-specific neural networks via supervised learning to imitate the action...
Ecological domains seeking to understand the environment and the behavior of species have received little attention in machine learning (ML), despite the fact that environmental changes have a significant impact on humans as well as ecosystems. Some ecological problems can be formulated similarly to other common ML applications, but there...
Western juniper (Juniperus occidentalis) encroachment has been associated with negative ecological and hydrological consequences including reductions in herbaceous production and diversity, deterioration for wildlife habitat, and higher erosion and runoff potentials. As a result, western juniper removal is a common and accepted rangeland management practice. Although studies evaluating the ecological...
Anomaly detection has been used in variety of applications in practice, including cyber-security, fraud detection and detecting faults in safety critical systems, etc. Anomaly detectors produce a ranked list of statistical anomalies, which are typically examined by human analysts in order to extract the actual anomalies of interest. Unfortunately, most...
We spatially discretize the Sn transport equation using the high-order (HO) discontinuous finite element method (DFEM) on HO meshes. Previous work provided a proof-of-concept for this spatial discretization method in X-Y geometry. Included in the present work, we derive a spatial discretization for the Sn transport equation in both X-Y...
Species distribution models (SDM), which quantify the correlation between the distribution of a species and environmental factors, are increasingly used to map and monitor animal and plant distributions in the context of awareness of environmental change and its ecological consequence. For perfect data, this is a straightforward classification problem from...
Forest management in the face of fire risk is a challenging problem because fire spreads across a landscape and because its occurrence is unpredictable. Additionally, management must be adjusted over time as unpredictable fire events are realized. Land managers have some control over the vegetation conditions that facilitate fire spread,...
Wheat (Triticum aestivum) is a highly valuable crop that makes up a large portion of the world’s food. However, breeding for improved varieties with desirable characteristics can be a challenge. This research examined two different issues wheat breeders deal with throughout the selection process all the way to production of...
High counts of fecal indicators, used to signal the potential presence of pathogens associated with untreated waste, result in the classification of water bodies throughout the United States as impaired. Nonpoint sources of unknown origin that contribute to fecal contamination make management of impaired waters challenging, as they are difficult...