Arpan Jani received his PhD in Business Administration from the University of Minnesota in 2005. He is currently an Associate Professor in the Department of Computer Science and Information Systems at the University of Wisconsin – River Falls. His current research interests include agent-based modeling, information systems and decision support, behavioral ethics, and judgment & decision making under conditions of risk and uncertainty.

The goal of my research program is to improve our understanding about highly integrated natural and human processes. Within the context of Land-System Science, I seek to understand how natural and human systems interact through feedback mechanisms and affect land management choices among humans and ecosystem (e.g., carbon storage) and biophysical processes (e.g., erosion) in natural systems. One component of this program involves finding novel methods for data collection (e.g., unmanned aerial vehicles) that can be used to calibrate and validate models of natural systems at the resolution of decision makers. Another component of this program involves the design and construction of agent-based models to formalize our understanding of human decisions and their interaction with their environment in computer code. The most exciting, and remaining part, is coupling these two components together so that we may not only quantify the impact of representing their coupling, but more importantly to assess the impacts of changing climate, technology, and policy on human well-being, patterns of land use and land management, and ecological and biophysical aspects of our environment.

To achieve this overarching goal, my students and I conduct fieldwork that involves the use of state-of-the-art unmanned aerial vehicles (UAVs) in combination with ground-based light detection and ranging (LiDAR) equipment, RTK global positioning system (GPS) receivers, weather and soil sensors, and a host of different types of manual measurements. We bring these data together to make methodological advancements and benchmark novel equipment to justify its use in the calibration and validation of models of natural and human processes. By conducting fieldwork at high spatial resolutions (e.g., parcel level) we are able to couple our representation of natural system processes at the scale at which human actors make decisions and improve our understanding about how they react to changes and affect our environment.

As a data scientist, I employ a variety of ecoinformatic tools to understand and improve the sustainability of complex social-ecological systems.  I also apply Science and Technology Studies lenses to my modeling processes in order to see potential ways to make social-ecological system management more just.  I prefer to work collaboratively with communities on modeling: teaching mapping and modeling skills, collaboratively building data representations and models, and analyzing and synthesizing community-held data as appropriate. At the same time, I look for ways to create space for qualitative and other forms of knowledge to reside alongside quantitative analysis, using mixed and integrative methods.

Recent projects include: 1) Studying Californian forest dynamics using Bayesian statistical models and object-based image analysis (datasets included forest inventories and historical aerial photographs); 2) Indigenous mapping and community-based modeling of agro-pastoral systems in rural Zimbabwe (methods included GPS/GIS, agent-based modeling and social network analysis); 3) Supporting Tribal science and environmental management on the Klamath River in California using historical aerial image analysis of land use/land cover change and social networks analysis of water quality management processes; 4) Bayesian statistical modeling of community-collected data on human uses of Marine Protected Areas in California.