No one sees the effects of climate change as clearly, or as early, as farmers. Changes in precipitation and increases in temperature can have a dramatic impact on crop yield, and the earlier that farmers can learn what type of weather is coming, the better they can prepare to protect the growing season. To that end, researchers at the University of Maine (UMaine) used imaging spectroscopy to predict the occurrence of water stress, caused by a deficit of water, in blueberry fields. Flagging the grower when the fields lack sufficient water is one way the technology is helping farmers to get to the root of the way changes in the environment are affecting their crop. Courtesy of iStock.com/2ndLookGraphics. A group of scientists from UMaine, the Schoodic Institute at Acadia National Park, and Wyman’s — one of the world’s largest suppliers of wild blueberries — found that when imaging spectroscopy is incorporated into crop models, the technology can help to inform growers as they evaluate irrigation routines and manage water resources to avoid damaging the crop. Imaging spectroscopy measures the light reflected off of objects as depicted in images captured by drones, satellites, and other remote sensing technology to classify and gather pertinent information about the objects. The technique precisely measures light across dozens, if not hundreds, of bands of colors. This reflectance spectra can depict nutrient levels, chlorophyll content, and other indicators of crop health. The information helps to build awareness before the harvest. In Maine, the vast wild blueberry barrens are central features of its eastern coast, along with the region’s sandy soil and the dense fog that usually blankets the region in the late summer. But the research team was able to pick its own season for gathering data. The researchers collected imaging spectroscopy data by deploying a drone equipped with a spectrometer to photograph Wyman’s wild blueberry fields in the town of Deblois, capturing visible and NIR light. The team then processed the images to measure reflected light spectra from the plants and gather information about chlorophyll levels and other properties that would help estimate the plants’ irrigation status and water potential. At the same time, the group collected small branches with leaves from the wild blueberry plants to manually assess their water potential and validate the spectra-based estimation. The pictures and samples were collected in the spring and summer of 2019, when the plants experienced peak bloom, green fruit, and color break. Graduate student Catherine Chan led the study, joined by UMaine faculty Daniel Hayes and Yongjiang Zhang, Schoodic Institute’s forest ecologist Peter Nelson, and Wyman’s agronomist Bruce Hall. “We couple spectral data and areas of known water potential in wild blueberry fields through machine learning, creating a model to further predict areas that may be water stressed,” Chan said. The results of both sets of models were comparable, demonstrating that imaging spectroscopy can accurately predict the presence of water stress in wild blueberry barrens at various times of the growing season. With the efficacy of the technology confirmed, the researchers said that scientists could easily conduct repeated measurements on small objects such as blueberry leaves. Understanding how to sustainably manage water resources to mitigate risk associated with present and increasing drought frequency is crucial to growers of wild blueberries and other crops. With a greater ability to predict problems in the field, the less of an impact drought will have at the dinner table. “This research provides key learnings to ensure the continued viability of wild blueberry crops for generations to come,” Hall said. Climate change is not the only threat to farmers or their crops. Freezing temperatures and pathogens have compounded crop struggles in recent years. Such threats have only heightened the need for predictive tools such as imaging spectroscopy and models that rely on it. “We envisioned and continue to promote this as a research and application tool to produce data and algorithms applied to questions and problems in forest, agricultural, and marine sectors of Maine’s economy,” Nelson said. The team’s research may have started with concern over the simple, small blueberry, but their solution for agriculture has the potential to grow to become much more.