Software
CA 30x30 Planning & Assessment Prototype
Proof of concept for a decision support tool developed in partnership with California Biodiversity Network participants through a co-design process. The tool can answer complex, real world natural language queries asked by conservation partner organizations, responding with reproducible, verifiable data summaries, charts, maps and text through careful integration of open weights language models and cloud optimized data.
Decision-Making for Land Conservation: A Derivative-Free Optimization Framework
A spatial planning tool that utilizes mixed-integer nonlinear programming (MINLP), thus can be paired with ecological software (e.g. population viability analysis). Existing spatial tools typically only allow linear inputs and discrete variables. However, our MINLP framework enables the use of linear and nonlinear inputs, as well as both continuous and discrete variables.
Conmin-CG: Hybrid Cubic Regularization of Conjugate Gradient Minimization Method
A quasi-Newton optimization algorithm that improves the step quality of conjugate gradient methods by selectively using cubic regularization. Compared to its non-regularized counterpart, this method exhibited fewer iteration counts and faster runtime when solving unconstrained optimization problems during numerical testing.
