WEST at ACP Siting and Environmental Compliance Virtual Summit

WEST staff are in attendance at ACP Siting and Environmental Compliance Virtual Summit this week and are participating in live and on-demand sessions.

The Intersection of Solar and Wildlife: What We Know and What Questions Remain“ – Wally Erickson, Presenter (Live Session)
Presentation Description: With ~300GW of solar to be installed in the next 10 years, it is important to understand the intersection between solar facilities and the surrounding wildlife. Over time, it will be important to support wildlife usage while reducing negative impacts caused by the development of these facilities. During this panel, we will hear from four experts on wildlife specific regulatory processes and recent research on wildlife use and potential impacts at solar facilities.

Case Studies in Effective Analytical Techniques to Aid in Siting Solar Energy Projects” – Wally Erickson, Presenter (On-Demand)
Presentation Description: Solar energy development continues to grow at a very fast pace throughout the US. In light of this rapid amount of development, site selection and infrastructure siting for project areas are important considerations to avoid and reduce impacts to natural resources. We provide three case studies illustrating technology and analytic approaches to siting of solar facilities. The first case includes the use of unmanned aircraft systems (UAS’s) for mapping important wildlife habitat (e.g. prairie dog burrow mapping) and for project layout development. The second example describes approaches using big game telemetry data and associated statistical analysis techniques to help understand and potentially resolve siting challenges between big game migration and solar energy. The third case study involves the value of incorporating effective statistical sampling strategies to map and estimate densities of sensitive plant species for both projects and potential mitigation sites.  All three examples emphasize the need for incorporating good siting principles to help minimize impacts and costs associated with solar development.

Aligning Energy Transition Policy with Endangered Species Conservation Needs” – Karen Tyrell, Ph.D., Presenter (On-Demand)
Presentation Description: The current administration’s energy transition policy has established timelines for increased renewable energy generation and at the same time set climate change response and biodiversity as planning priorities. These may present incompatibilities, as species conservation efforts by renewable energy project developers are often encouraged to occur on an isolated project scale poorly suited for responding to climate shifts or maintaining biodiversity. Hence, development may lead to piecemeal conservation efforts which are ultimately limited in value. Further, conditions that made the administration’s priorities necessary are contributing to additional endangered species protection needs as new threats are recognized. Thus, the principal goal of the Endangered Species Act (ESA) to restore populations against the threat of extinction may become increasingly difficult to achieve without adapting how the law is applied such that environmental benefits of limiting carbon emission can be more fully realized. Recent habitat conservation plans have predicted and mitigated impacts to federally listed wildlife species on a habitat-acre basis, often without the benefit of guidance based on climate change and biodiversity planning. We will describe how this can influence species distribution and population stability, and will present strategies that can bring into alignment the need for project-specific ESA compliance with broader biodiversity and climate resiliency goals.

Deep Learning and Computer Vision for Wildlife Observation at Renewable Energy Sites” – Mikey Tabak, Ph.D., Presenter (On-Demand)
Presentation Description: Camera traps, acoustic detectors, and crewless aircraft (drones and fixed-wing aircrafts) flights are often employed wind and solar facilities to remotely evaluate wildlife. These remote sensing operations collect large amounts of images or sound files that must be processed and analyzed before the data can be used to gather useful information. Deep learning provides a tool to automatically and rapidly process these data. We used computer vision and deep learning to build models that automatically process images and acoustic recordings of wildlife. Specifically, we evaluated the effectives of image classification, object detection, and object segmentation computer vision models to analyze remote sensing data. We found that object detection models are able to rapidly classify, detect, and count animal species in camera trap images, as well as images from flights of drones and fixed wing aircraft, with accuracies of 90-98%. We also found that image classification models were able to classify bat species from acoustic recordings with 93% accuracy. We found that object detection and object segmentation models are more effective than classification models at removing empty images from datasets, and they have the advantage of automatically counting and locating animals within images. These models can rapidly (100-1,000 images per minute) process data on laptop computers. Thus, these models can be deployed for continuous monitoring and allow for data acquisition in “real time.”

Expanding Corporate Sustainability Reporting: the role of vegetation at ground-mounted solar facilities” – Elizabeth Markhart, Presenter (On-Demand)
Presentation Description: Ground-mounted photovoltaic solar is similar to corporate campuses, parks, and private land holdings in that they all require regular vegetation management. At solar facilities, ecologically-based approaches to vegetation restoration and management allow for reporting sustainability metrics such as biodiversity, pollination services, soil health, or watershed enhancement. Attaining sustainability requires achieving measurable standards through a carefully executed project life-cycle plan. In this presentation the process for carrying out successful vegetation restoration and management in parallel but separate from engineering and construction of the energy facility. This process will illustrate a life-cycle framework, the collaboration among people, and the key cost factors leading to successful sustainability reporting from project planning all the way through to decommissioning. Critical to this success is measuring the health and condition of vegetation over time. We will cover the measuring and reporting tools for both sustainability reporting and keeping long-term costs in check. Vegetation is a living system that responds through time to management practices and the environment. We will provide the fundamentals of practicing the science of restoration so early success is cost effectively maintained over time.

Initial Results – A Multi-Sensor Approach for Measuring Bird and Bat Collisions with Wind Turbines” – Jennifer Stucker, Ph.D., Presenter (On-Demand)
Presentation Description: Post-construction mortality monitoring is standard at land-based wind farms. Because this approach is not applicable for offshore wind, collision detection methods are necessary to assess potential impacts of offshore wind development on volant wildlife. WEST is leading the validation of an automated, multi-sensor system for quantifying bird and bat collisions with wind turbines. The DOE has funded a collaboration among TNO, NREL, and WEST in advancing the development of TNO WT-Bird® collision detection system. The system includes non-metallic acceleration sensors mounted inside turbine blades to detect collision impacts, and cameras installed at the base of the turbine to record collision events. The primary objective is to optimize the WT-Bird® system to detect small bird and bat collisions during both daytime and nighttime hours. Three major technological advancements resulting from the project include: 1) improving the sensitivity of acceleration sensors to detect collisions as small as 8 grams, 2) integrating machine learning algorithms to process imagery data collected by the cameras to automatically classify birds or bats and verify collision, and 3) creating a launching system and projectiles of multiple sizes to realistically simulate collisions. This presentation will report on the initial results on the increased sensitivity of the acceleration sensors for detecting collision and the challenges of collision testing on a full-sized turbine at NREL during a pandemic.