AI-Supported Virtual Reality Tools to Support Grief Counseling Through Gamified Therapy

AI-Supported Virtual Reality Tools to Support Grief Counseling Through Gamified Therapy is sponsored by CITRIS and the Banatao Institute (UC Santa Cruz). This project, currently funded internally by CITRIS and the Banatao Institute at UC Santa Cruz, pioneers applications of generative AI in mental health through adaptive storytelling and explores the impact of immersive VR and spatial audio on well-being, specifically for grief c…

Funded Projects and Events – CITRIS and the Banatao Institute – UC Santa Cruz Accessibility Navigation Project The project aims to create an alternative navigation/map tool for UCSC, centered on accessibility. Currently, campus navigation poses several challenges for members of the campus community with disabilities (e.g., steep inclines, pollen, unpaved routes, uneven roads, etc.).

These challenges mean that campus accessibility is limited or the current means of access are laborious (i.e., having to wait for a shuttle). Most students with disabilities often have to rely on shuttle services or navigate the campus with limited mobility options, alienating them from the larger student community. The team aims to create a navigation tool for students based on their preferences concerning their bodies’ capabilities.

The new navigation model will aid the user in finding alternative routes or paths to engage with based on their needs. This will take into account a variety of disabilities, ranging from physical impairments to more transient needs, such as those prone to migraines needing to avoid sunlight.

The study will incorporate a research through design model that will engage with various student stakeholders through surveys, interviews, walkthrough studies, codesign workshops, and citizen science models.

For the citizen science models, due to the wide number of variables we aim to measure, we require the use of foot sensors to map the wider variables, such as stress points, tactile experiences of using different routes, and the various route alternatives appropriate for the user’s needs.

Bhavani Seetharaman, Graduate, Computational Media Aarna Pathare, Undergraduate, Bioinformatics Nicolett Nufio, Undergraduate, Cognitive Science AIRWISE aims to address the problem of gaps within air quality monitoring networks. To do this, the team will develop a low-cost, solar-powered network of air quality sensor nodes that can operate independently of WiFi.

Currently, the best air sensors on the market, PurpleAir sensors, do not meet these criteria and are expensive for low-income communities. The cheapest in-stock sensor is $240 and requires WiFi to upload data. Communities that are impacted by poor air quality and unreliable WiFi cannot easily install these air sensors to obtain proof of their substandard environmental conditions.

The only option is to spend thousands of dollars on these sensors and only install them in limited areas. In addition to these impacted communities, farms are often heavily impacted by poor air quality. In the surrounding areas, pesticides and other gases impact the lives of people living there.

WiFi is often unreliable across a large, rural farm, so this air quality data is also difficult to collect. These rural and agricultural zones are exactly where monitoring is needed to protect workers and nearby communities. Another issue the team aims to address is wildfire detection, which is especially important because many wildfires start in remote areas with no WiFi and then later spread to populated communities.

Placing AIRWISE nodes in areas susceptible to wildfires can provide an early warning when a wildfire has started, or even help develop a prediction model to determine whether there is a high risk of wildfire. This can be implemented by setting threshold values for humidity, temperature, and particulate matter (PM) measurements. One more route the team wants to pursue is mounting these sensor nodes on drones.

This would help analyze air quality over large areas of rural land and quickly create detailed maps of where the air quality is the poorest, which would be a difficult task for fixed, ground-based nodes. The sensor nodes will use LoRa (Long Range) radio waves to communicate with one another. Each node will measure particulate matter (PPM 1, PPM 2.

5, and PPM 10) and additional quantities such as humidity, temperature, air pressure, and VOCs. Each node will send all its data in a packet to a router node, which aggregates, processes, and uploads the data. This data will be publicly displayed on a frontend with a live feed of air quality measurements from our sensors.

The sensor nodes do not need to be connected to WiFi and can be placed in semi-remote areas with little to no maintenance needed, as their batteries will be charged with an included solar panel. The router node will need to be connected to WiFi and power, but can still be stationed miles away from the sensor nodes and reliably receive data.

For LoRa communication, we will use Meshtastic, an open-source community-based mesh network solution for radio communication. This has the additional benefit of increasing our range when other Meshtastic community members set up LoRa nodes that can repeat our messages and serve as intermediaries.

Sankritya Rai, Undergraduate, Computer Science Charan Nemaru, Undergraduate, Computer Engineering Theodore de Swiet, Undergraduate, Robotics Engineering Julius Villa, Undergraduate, Computer Science Gateways Digital Literacy Jail Courses Music-making serves as an accessible, culturally resonant entry point for students who may not see themselves represented in traditional academic or technical pathways.

Digital music tools invite experimentation and emotional expression while building essential digital competencies such as file navigation, editing workflows, and creative problem-solving. This approach creates a learning environment that feels empowering, relevant, and joyful. Alongside this, the team’s structured design process guides students through planning, prototyping, revising, and completing a final project.

It becomes a transferable blueprint that supports follow-through, organization, and intentional project development during incarceration and upon reentry. This directly addresses a major gap in carceral education: students are taught skills, but rarely given a consistent process for building and completing projects.

Gateways will continue using open-source tools such as Blender, ensuring students can access creative technologies post-release without financial barriers. Classes also integrate professional development practices such as portfolio building, interview preparation, and digital identity skills.

By combining creative technology, digital skill-building, music-making, and structured design practices, Gateways aims to reduce the digital divide and strengthen reentry outcomes. The project’s approach emphasizes community, creativity, and long-term empowerment, offering students who are incarcerated not just tools, but pathways, confidence, and sustainable growth beyond release.

Robin Pannu, Undergraduate, Legal Studies Jackie Eskelin, Undergraduate, Sociology Daisy Sanchez, Undergraduate, Sociology Amy Urzua, Undergraduate, Sociology Small farmers often find out about crop damage or pest outbreaks after they have grown into a major problem, when they are spotted during walkthroughs.

While large farms can afford to use AI and robotic survey data to inform early intervention procedures, small farmers must still deal with these avoidable losses. There is a need for a cost-effective, easy-to-use system which lets farmers discover destructive circumstances before they become major losses, without labor-intensive inspection.

Morgan Masters, Graduate, Electrical & Computer Engineering Jake Lee, Graduate, Electrical & Computer Engineering Dhimant Khuttan, Graduate, Electrical & Computer Engineering Andrea Arreortua, Undergraduate, Computer Science Audrey Luan, Undergraduate, Robotics Engineering Cole Bickell, Undergraduate, Robotics Engineering Connor Bengston, Undergraduate, Electrical & Computer Engineering Task Conditioned Prosthetic Vision Simulator Over 200 million people worldwide suffer from retinal degenerative diseases, causing permanent blindness.

Retinal prostheses electrically stimulate remaining retinal cells to create visual perception. However, current devices like Argus II provide only 60-400 electrodes versus the natural retina’s 1 million cells, creating a severe information bottleneck. Current prosthetic vision systems use static encoding, treating all visual information equally.

A dangerous stove edge receives the same processing as irrelevant wall texture. Users see grainy, unclear images lacking detail for daily tasks like navigating, grasping objects, or reading signs. This is why 60% abandon their devices within a year.

The core challenge is the difficulty of showing what matters the most with only 400 “pixels” available. Current systems waste bandwidth on random information instead of intelligently prioritizing safety hazards, graspable objects, and readable text. The team will develop a hybrid multi-task prosthetic vision encoder that uses artificial intelligence to automatically understand and prioritize visual information.

Instead of blindly converting pixels to electrical signals, this system uses a vision-language model called CLIP that has been trained on 400 million images to understand the semantic meaning. As a result, the users will have clearer, safer, and more useful vision. The team will implement this system entirely in software using Python, PyTorch (for neural networks), and pulse2percept (for realistic vision simulation).

The CLIP encoder remains frozen (pretrained), while we train only small adapter networks on synthetic and real-world images with ground-truth labels for edges, objects, and text regions. Performance will be validated by comparing the system against three baselines: static downsampling, edge-only detection, and single-task optimized encoders.

The project uses scalable cloud infrastructure (Google Colab/AWS) for training and cloud storage (Google Drive/S3) with GitHub version control for reproducibility. This cloud-native approach would allow scaling for greater datasets. The system is designed for edge device deployment like nanos, making it ready for real-time hardware integration and future clinical trials.

Nathan Lee Yang, Undergraduate, Biomolecular Engineering and Bioinformatics Nathan Lam, Undergraduate, Biomolecular Engineering Aljon “Jiro” Claveria, Undergraduate, Biomolecular Engineering Environmental NeTwork Sensors (ENTS): Low-Cost Scalable Hardware for Studying Agricultural Field Sensors With the rising demand for sustainable agricultural practices and effective environmental monitoring, the need for reliable data on soil and plant health is essential.

However, existing commercial solutions frequently fall short in meeting the specific needs of farmers and researchers, who often face limitations in range, durability, and ease of deployment. For instance, according to the USDA, only 13% of farmers in the U.S. use soil moisture sensors, with most relying on traditional, intuitive methods for irrigation timing.

While various commercial solutions for outdoor and agricultural sensor networks have emerged, users often face challenges with the longevity of these products.

According to the Ag Technical Program Specialist at the Santa Cruz County Resource Conservation District, many small farmers have initially adopted a company’s platform, only for the company to later exit the agriculture or wildland market, leaving them with unsupported and obsolete systems. This trend underscores a need for accessible, user-friendly, cost-effective, and long-lasting agricultural sensors.

In response, we have developed an open-source hardware and software platform for outdoor sensor networks that will fill a critical gap that is impeding the widespread adoption of innovative technologies for data-driven land management. The ENTS (Environmental NeTworked Sensor) project is a low-power, customizable platform that empowers farmers and researchers with a user-friendly solution for large-scale environmental monitoring.

The ENTS hardware is designed to capture a variety of sensor signals, creating an affordable, energy-efficient alternative to proprietary technologies. The collected data are transmitted to a software platform, allowing users to visualize trends and analyze key metrics such as soil moisture and temperature in real-time.

By seamlessly integrating robust hardware with an intuitive software dashboard, the ENTS platform provides a comprehensive solution that empowers sustainable agricultural practices and enhances environmental research.

The next phases of the ENTS project involve strengthening the hardware’s battery efficiency, expanding compatibility with additional sensor types, gathering feedback on the system from local farmers, and increasing durability through waterproofing for consistent outdoor use. Additionally, a large-scale test will be conducted in collaboration with researchers at UC San Diego, Northwestern University, and Georgia Tech.

This collaborative field test will utilize the ENTS platform to gather data on novel sources of electricity that can be harvested from nature itself. As an open-source initiative, ENTS will make this extensive dataset available to the research community, serving as a foundational resource and encouraging further innovation in environmental monitoring.

John Madden, Graduate, Electrical and Computer Engineering Miles Johnson, Undergraduate, Electrical and Computer Engineering Ella Ferraz, Graduate, Electrical and Computer Engineering Alec Levy, Undergraduate, Computer Engineering Caden Jacobs, Undergraduate, Robotics Engineering Varun Sreedharan, Undergraduate, Computer Engineering Charlie Chesney, Graduate, Environmental Studies UCSC Blueprint is addressing a critical gap in career exploration for K-12 students in Santa Cruz County through partnership with Your Future is Our Business (YFIOB).

Despite many career opportunities in the region, students, especially from underserved communities, often lack access to career guidance and industry connections. The team has developed an assessment platform with YFIOB that shows promise but needs further enhancement.

The project will expand on our initial implementation in three key ways: Enhanced Assessment System: Refining the career matching algorithm to offer more detailed, localized recommendations based on student interests, skills, and regional industry demands.

Data-Driven Insights: By introducing advanced analytics, the project will help YFIOB understand career trends across Santa Cruz County’s diverse demographics, enabling more targeted support. Local Industry Integration: Building a system to connect students directly with local career opportunities, internships, and mentorship programs, making career exploration more practical.

A team of 50 student developers, experienced in nonprofit projects, brings the skills and community insight needed to realize this vision. This project leverages previous platform experience while adding features tailored for YFIOB’s needs.

Erika Wu, Undergraduate, Computer Science Malco Salcedo, Undergraduate, Computer Science Mandar Patil, Undergraduate Emil Wilson, Undergraduate Kartikeya Kumaria, Undergraduate Akshay Kamath, Undergraduate Brenda Aceves, Undergraduate AI-Supported Virtual Reality Tools to Support Grief Counseling Through Gamified Therapy Grief remains an under-explored area in immersive technology, with few existing tools that offer experiential or gamified support for emotional processing outside of traditional therapy (Alvarenga & Kobenova, 2024; Chen et al, 2024; Roth et al, 2019).

In mental health, gamification and VR have shown potential in promoting emotional resilience and mental well-being, yet there are limited approaches that directly address grief or loss in a personalized, virtual format (Marchioro et al, 2024). Our project introduces an immersive, gamified experience using virtual reality (VR) and generative AI to support individuals dealing with grief.

By combining AI-driven storytelling and interactive VR environments, this platform offers a tailored experience, guiding users through a personal and empathetic journey to process and manage grief.

Grounded in theories of immersive cognition and emotional engagement (Makransky & Peterson, 2021), our VR experience leverages AI to create dynamic storytelling that adapts to user input, providing an evolving narrative that mirrors the user’s emotional journey.

The project includes three primary technological innovations: Generative AI: AI will generate responsive story elements that reflect individual player interactions, enabling a dynamic, personalized experience that can help users feel understood and supported.

Previous work builds on using AI for VR content (Kobenova, DeVeaux, and Parajuli, 2024; De La Torre, Fang & Huang, 2024) and grief storytelling (Ibrahim, 2023), but not in combination of the two. Spatial Audio for Emotional Immersion: Incorporating spatial audio with calming soundscapes aims to create an immersive environment that enhances emotional regulation, helping users remain present and engaged in the experience.

Previous research supports the use of immersive, spatial audio for enhancing well-being (Greenberg et al, 2021). Human-AI Collaboration in Grief Support: By designing this as a multi-user VR setting, our platform supports collaborative healing, either as a solo experience with AI support or a shared experience with family members or therapists.

We are partnering with Jacob’s Heart Cancer Support Services, a nonprofit in Santa Cruz that supports families dealing with terminal illness and loss. Working with grief counselors and psychologists, we will co-design the VR curriculum, integrating feedback and evidence-based strategies to ensure the experience is beneficial and respectful.

This partnership provides direct access to end-users, enabling a participant-centered design approach. This project contributes to the field by (1) pioneering applications of generative AI in mental health through adaptive storytelling, (2) exploring the impact of immersive VR and spatial audio on well-being, and (3) advancing novel algorithms and gameplay techniques that support human-AI collaboration in therapeutic applications.

By addressing grief through VR, we aim to create an accessible, scalable tool that offers a unique pathway to emotional healing. Amina Kobenova, Graduate, Computational Media Piper Stickler, Undergraduate Wildfire Management with UAV Systems To address the intensifying threat of wildfires in California, our project aims to revolutionize wildfire detection through the use of multi-UAV (Unmanned Aerial Vehicle) systems.

These UAVs will be equipped with advanced sensors capable of capturing critical environmental data, including temperature, humidity, wind speed, atmospheric pressure, and particulate levels. By targeting high-risk and remote areas, these UAVs can provide real-time data where traditional ground-based or manned aerial units face significant limitations.

The drones will be designed with modular components, allowing for easy upgrades and replacements, as well as fail-safe mechanisms and energy-efficient designs to maximize reliability and flight endurance even under challenging conditions. The data collected by these UAVs will feed into predictive algorithms that model wildfire behavior with enhanced accuracy.

These algorithms will forecast key factors such as fire spread direction, speed, resource needs, proximity to critical infrastructure, and the effectiveness of ongoing suppression efforts. By incorporating machine learning techniques, the algorithms will continuously improve over time, providing increasingly accurate predictions.

These outputs will be visualized in user-friendly formats, ensuring seamless integration with existing emergency management systems used by firefighting agencies like Calfire, ultimately enabling more informed and timely decision-making during wildfire events. To ensure the system’s reliability, a multi-phase testing process will be implemented. Initial testing will occur in simulated environments to refine algorithms and workflows.

This will be followed by small-scale live testing in controlled conditions to validate the drones’ ability to gather and transmit data effectively. Finally, deployment testing will take place in simulated wildfire scenarios. This iterative process will ensure the development of a robust and reliable wildfire management tool.

By providing an effective tool for early wildfire detection and management, this project has the potential to significantly reduce wildfire-related greenhouse gas emissions, protect vulnerable communities, and preserve critical ecosystems.

Under-resourced and marginalized communities, which often face the greatest risks from wildfires, will particularly benefit from the improved safety and reduced economic strain that this system can provide. Additionally, by reducing wildfire intensity, the project could help lower insurance premiums and associated costs for communities across California.

Overall, this initiative combines technological innovation with education, sustainability, and equity, setting a new standard for wildfire management and contributing to the resilience of both local and global communities.

Alexander Aghili, Undergraduate, Computer Science & Mathematics Andy Wu, Undergraduate, Robotics Engineering Nathan Pham, Undergraduate, Computer Engineering Parsh Gandhi, Undergraduate, Robotics Engineering Aditya Davanam, Undergraduate, Computer Science Gabriel Jaimes, Undergraduate, Computer Science Jordan Miller, Undergraduate, Electrical Engineering Gateways Digital Literacy Jail Classes The carceral system in California has a deep history of strategically placing prisons and jails in a way that geographically isolates the incarcerated community from outside communities.

Additionally, prisons and jails are underresourced. Due to this disconnect with the rest of society, folks who are incarcerated cannot easily access modern and technical skills, both of which are crucial for keeping up with society both socially and professionally post-release.

This, along with the physical locations of jails and prisons being placed in very isolated areas of California, causes a huge disconnect between the incarcerated community and communities who do have access to technology, the space to develop their skills, and the ability to keep up with the rapidly changing job market.

Due to this, recidivism rates in California are high due to recently released folks not being able to access the same skill development and technology as other communities.

People who are incarcerated and later reintegrated into society have a harder time adjusting to their roles, especially as they have fewer opportunities to remain up to date with the skill sets many job positions require, largely due to a lack of access to the latest technology. Because of this, people who have been recently released are more vulnerable to becoming incarcerated again.

In the last three years, the Gateways team has shifted from online computer literacy classes back to in-person facilitation at the Rountree Men’s facility in Watsonville, CA. These courses have ranged from basic computer skills such as getting to know the very basic tools of a MacBook, to practicing intro coding skills and creating a web page via Adobe Dreamweaver.

Classes are popular in the facility and serve as a safe, co-learning environment for both facilitators and students. Additionally, Gateways has partnered with three formerly incarcerated filmmakers, where students have collaborated on video editing, filming, and overall creating a connection with their partner contact in developing impactful storytelling media.

These three projects emphasize using tech as a tool to tell important stories in an accessible and digital format, as well as the importance of collaboration and relationship building in the partnerships that passionate student leaders in the Everett Program seek to be a part of. These jail classes consist of a 3-course computer literacy series, six weeks each.

Though the project team is still in the process of working towards expanding their classes to Soledad prison, they are focusing on ensuring that the classes they already hold are as accessible and fun as possible. Because of this, they are switching from using Adobe platforms to open-source software programs this year, including Blendr and Krita; two digital art animation platforms.

With curriculum that also integrates personal and professional development activities, such as portfolio development and interview preparation, classes make room for practicing skills that students can apply to new workplace environments post-release.

Emily Ball, Undergraduate, Sociology with GISES Alex Guzman, Undergraduate, Sociology with GISES and Legal Studies Quynh-Thy Hoang, Undergraduate, Sociology with GISES and Education Mobile App for Interaction with an Electric Tractor Despite considerable profits, California has faced an agricultural labor shortage for the past decade, with surveys indicating significant difficulties in securing necessary labor.

Farmers have attempted to address this issue by transitioning to less labor-intensive crops and offering higher wages, but these measures have had limited success due to the physically demanding nature of profitable California cash crops. Agricultural labor also exposes workers to various occupational hazards, including pesticide exposure and inadequate training for heavy machinery operations.

The conventional agricultural approach relies on labor-intensive tasks, time-consuming processes, and excessive use of pesticides, resulting in a workforce shortage, increased operational costs, unsafe working environments, and reduced efficiency. Our team is committed to mitigating these challenges by optimizing the existing autonomous navigation software for the Amiga robot UCSC has at the CASFS farm.

The Amiga is a small and adjustable electric tractor developed by farm_ng for farmers to automate manual tasks, receive real-time updates, and minimize maintenance and fuel expenses. Throughout our project, we will develop a mobile application equipped with a virtual joystick, enabling remote control of the electric tractor from any point on the farm.

Furthermore, this application will facilitate cooperative control, allowing two farmers to manage the tractor via their mobile devices. This provides farmers with a convenient and versatile means of overseeing tractor operations across the farm. Additionally, the application incorporates a virtual stop button for enhanced control and safety that can stop the tractor at any time.

Our project aims to enhance California’s farming practices by focusing on organic farming. Organic farming offers more benefits, such as soil quality preservation, improved fertility, and biodiversity. Within our project, we will create a mobile application with a virtual joystick to enable remote tractor control from any location on the farm.

Similarly, this mobile application will have an emergency stop button, ensuring the safety of farmers on the farm. The key benefits of the application include: Less Physically Intensive Operations: The application enables tractor control using a mobile device, reducing the physical intensity of material movement, weeding, planting, and transportation.

Efficient Cooperative Control: Two farmers can manage the tractor via mobile devices, streamlining various agricultural tasks and enhancing overall efficiency. Enhanced Control and Safety: The virtual stop button provides farmers with increased control and safety, allowing them to stop the tractor at any moment.

Smooth Integration into Organic Farming: The application seamlessly integrates an autonomous tractor into an organic farming environment, improving overall farm efficiency. Empowering Farmers with the Right to Repair: The application allows farmers to repair and maintain their equipment, returning control to them.

Incorporating these enhancements to the existing autonomous navigation system holds substantial potential for small-scale organic farmers, delivering an efficient tool adaptable to a range of agricultural tasks, including weeding, planting, loading, and material transport. Rather than replacing farmer involvement, our solution is designed to support farmers, enhancing their efficiency while minimizing the physical risks of farming.

Oliver Fuchs, Undergraduate, Robotics Engineering Katherine Rogacheva, Undergraduate, Robotics Engineering Milos Suvakovic, Undergraduate, Computer Science Sam Leveau, Undergraduate, Robotics Engineering Gateways Digital Literacy Classes The structure of the California incarceration system causes a disconnect between the incarcerated community and the rest of the state population.

Prison and jail facilities are underresourced in terms of access to learning technical and modern skills, both of which are crucial for reentry following release. This causes a disconnect between the incarcerated community and communities who do have access to the technology and are given the space to hone their skills, both technical and personal.

Largely due to this disconnect, recidivism rates in California are especially high compared to the rest of the country because recently released folks have not had access to the same skill development and technology as other communities.

People who are incarcerated and later reintegrated into society have a harder time adjusting to their roles, especially as they have fewer opportunities to remain up to date with the skill sets many job positions require, largely due to a lack of access to the latest technology. In the last year post-COVID the Gateways Project taught computer literacy using Adobe Illustrator and iMovie inside Watsonville’s Rountree Mens’ facility.

These classes have been popular amongst the facility’s population, and we are ready to dive into another year of engaging in peer-to-peer learning through our digital literacy classes. Additionally, Gateways has partnered with two formerly incarcerated filmmakers in utilizing the resources given to our students through the university and collaborating with them to uplift their stories.

Both of these projects reflect the importance that Gateways emphasizes on digital media in storytelling, advocacy, and in fostering community. This year, Gateways is expanding our digital literacy courses to the Santa Cruz Blaine Women’s Facility. Our education initiative provides comprehensive digital design classes to incarcerated individuals in two Santa Cruz County facilities.

This initiative not only benefits the job, health, and reentry outcomes of incarcerated students but also increases community engagement in advocating for the rights, dignity, and lives of those currently incarcerated. The jail education initiative consists of a 3-course digital literacy series, 6 weeks each, covering topics such as Adobe Illustrator, Photoshop, Dreamweaver, and Rush.

Providing computers including Adobe Software, which is offline accessible due to the lack of wifi and internet connection in jail facilities, gives students at Santa Cruz County facilities opportunities that have never before been offered.

Gateways’ curriculum also integrates personal development and interpersonal communication, preparing students with a set of in-demand technical and practical skills necessary to secure employment and excel in new workplace environments.

Mia Perez, Undergraduate, Sociology Katerina Bajaj, Executive Fellow – Everett Program, Sociology Ivanna Mendez, Undergraduate, Legal Studies Mariana Marino, Undergraduate, Sociology Derrick Valencia-Murillo, Undergraduate, Sociology Katheline Vanegas, Undergraduate, Sociology Greenhouses equipped with sensors can increase crop yield efficiency by reducing resource usage such as water, fertilizer, and lighting.

Current monitoring systems for protected agriculture are expensive, energy-demanding, and require frequent human intervention. We propose a chance to leverage existing greenhouse control systems by creating an ultra-low power open-source sensing node that is powered by and communicated to via the existing supplemental lighting commonly found in protected agriculture.

This approach will yield reduced costs in both power consumption as well as labor. The key technologies that we will develop to achieve this goal are Visible Light Communication (VLC) and Radio Frequency (RF) backscatter. Traditionally, VLC has used the high-speed toggling of Light Emitting Diodes (LEDs) to send a wireless signal to a solar panel receiver.

The main benefit of using VLC is that it functions as both a source of energy for the low-power sensing node as well as a channel to send data or commands to the node. Furthermore, in our case, the LEDs can also be used as the aforementioned supplemental lighting for greenhouses.

RF backscatter is a passive communication technique that modulates and reflects RF waves instead of generating, which enables wireless communication that operates at orders of magnitude lower power than traditional WiFi or Bluetooth.

By using LiFi to send data to the sensor nodes (downlink) and RF backscatter to transmit data from the sensor nodes (uplink), we can implement a novel ultra-low power wireless sensor network that will be ideal for greenhouses. Our work primarily aims to improve the techniques used in VLC to further enhance communication range and resilience to noise by developing a chirp spread spectrum -based modulation technique.

This modulation technique will be more robust in greenhouse environments where there is significant noise (in the form of sunlight) as it encodes data in the phase of the signal rather than its amplitude. In addition, our work involves deployment of this VLC/RF-based wireless sensor network in the UCSC Coastal Biology Greenhouses to go beyond the lab bench and directly benefit actual greenhouses.

Jack Lin, Graduate, Electrical and Computer Engineering Yawen Guo, Graduate, Electrical and Computer Engineering Matt Kaltman, Undergraduate, Electrical and Computer Engineering Firouz Vafadari, Graduate, Computer Science and Engineering Moving away from fossil fuels to increase our reliance on renewable energy sources is one key step in meeting climate goals.

However, renewable energy facilities can negatively impact ecosystems (Naugle, 2011), including birds via impact collision fatalities (Conkling et al. , 2022). Bird diversity declines negatively impact the ecosystem services they provide: pollination, seed dispersal, insect and rodent control, decomposition, and cultural importance (Whelan et al.

, 2015). Living Solar Panels aims to be the first living-cactus electricity farm. The farm plot will demonstrate the ability of Living Solar Panels to provide carbon-negative and biodiversity-friendly electricity.

The plot will serve as a living testbed to explore how much electricity can be harvested from 20 living cactus stems, as well as providing undergraduate learning opportunities. Because cacti absorb and sequester CO2, Living Solar Panels could become a carbon-negative renewable energy source, thereby decreasing greenhouse gas emissions and atmospheric carbon while avoiding potential impact collisions to birds.

Living Solar Panels harvest electricity from the electrical potential that naturally forms across a cactus stem as a consequence of the Crassulacean Acid Metabolism (CAM) photosynthetic pathway. Plants that undergo CAM uptake carbon dioxide (CO2) during the night, not during the day like most plants (Gibson and Nobel, 1986). CAM plants store nighttime CO2 as malic acid, and during the day, it is broken down