Active data science & sustainability research

Problem

The insect emerald ash borer has ripped through forests in the eastern US, devastating native ash trees at an alarming pace. Current modeling efforts by academic and public scientists are critical for understanding how this invasive species impacts both forests and urban greenspaces.

Solution

We are working with state entomologists to validate spatial models associated with a 10-year dataset collected in the state of Connecticut. Using information gleaned from ecological data maps are being produced to track impacts. To this end, we are providing GIS and statistical modeling consulting.

Applicability

Invasive species are one of the leading causes of biodiversity decline, and they also have significant impacts on economics and human health. Often one of the hardest challenges is just racking the impacts of invasive species, especially if containment measures have not succeeded. Quick turnaround is important for these modeling efforts.

‍

Problem

Smallholder or family farms have limited space and often rely on a diverse base of saleable products. However, getting the best spatial positioning out of all profitable crops is a surprisingly difficult calculation - even if a computer is provided with perfectly accurate data.

Solution

Rather than trying to find the perfect layout, we have developed algorithms in which basic requirements such as crop diversity, annual budgets, and land surface can be used on a per-farm basis. These algorithms use an iterative, evolutionary process to return a range of options to inform planning.

Applicability

These tools can be modified for any range of small-scale farming systems, including organic vegetables, urban farming systems, or intercropping trials. Due to their speed and flexibility, we can customize tools to provide reactive answers in real-time.

Challenge

Agrochemicals deal with all the environmental stressors found in the field. Even the most robust products become less effective in extreme temperatures or periods of plant stress. Pinpointing which conditions are responsible given the complexity of climate and local environments.

Solution

Using only survey data and locations from-end users, we can identify which extreme environmental changes impacted product performance. Working these models we can find critical thresholds specific to farming regions, such as temperature cutoffs.

Applicability

Such analyses are valuable to product development teams seeking to improve usage recommendations, end-users like farmers or orchardists, and can help avoid unnecessary use of products under poor application conditions.

Challenge

Ag professionals are interested in trying new practices to diversify farms. However, given the extremely large number of potential changes to crops and product usage, it's difficult to estimate long-term outcomes.

Solution

We developed a straight-forward tool to simulate 5-year outcomes based on starting conditions. Rather than generating a forecast, this tool serves as a way to look at "what if scenarios" where growers can see a range of potential economic outcomes based on both large and small management decisions.

Applicability

A diversified farm economic outcomes tool will be helpful to illustrate the potential gains and risks when adopting new varieties, rotations, or intercropping strategies. Such a tool will also help organizations marketing to local stakeholders interested in diversified agriculture.

‍

Challenge

Newly emerging pests require regionwide management strategies. Predicting the likely locations for spreading invasive, pest species is critical for removal efforts.

Solution

Working with collaborators in agricultural extension and integrated pest management, we are developing a data pipeline for analyzing data on newly emerging pest insects. These forecasts are location-specific and provided as web tools to serve professionals in the plant protection industry and government.

Applicability

The cyberinfrastructure surrounding these tools can be applied to any emerging pest or pathogen with enough prior data. Our programming and domain knowledge developed on this project is ready-made for other agricultural or forest systems dealing with newly emerging devastating pests.

Challenge
Invasive plant management is an established component of habitat improvement in managed forests. However, it is unclear how invasive plant removal might positively impact wildlife.

Solution
We analyzed data collected by non-profits and academic institutions in the northeastern United States on invasive weeds. By providing data analysis services and data visualization, we are able to quickly produce results for publications and bulletins advising land managers.

Applicability

The results of our statistical analyses suggest that some invasive plants are worse for wildlife than others, and that high-quality native plant should replace invasive plants in management scenarios.

Challenge‍

Crops can often be pollination limited. To maximize yields, the correct timing and intensity of pollination services can lead to significant payoffs. In cacao production, hand-pollination can impact the size, number, and quality of fruit simultaneously. We have developed structural equation models to leverage large-scale, long-term data to determine the ideal hand pollination rates for cacao trees.

Solution

We have built a framework for cleaning and analyzing farm data from orchards and other cultivated trees and developed a Python pipeline for fitting statistical models quickly and accurately. 

Applicability

The resulting outputs completed by EcoData Technology have been developed into a proprietary web application to meet the needs of end users in the cacao industry.