By Lulu Chen, Intern at the AgAID Institute, Washington State University
Can data be a game changer for farmers in the face of climate change? Farmers are at the forefront of risk and uncertainty in the face of a rapidly changing environment. Irregular weather patterns, severe temperatures, and shifting precipitation levels create significant challenges to agriculture worldwide. These uncertainties have an influence on crop production, resource management, and agricultural sustainability. However, a ray of optimism emerges among the chaos: the power of data-driven decision-making (yes, I’m a student specializing in Data Science).
As technology and innovation advance, so does the potential for data-driven decision-making to transform how farmers adapt to and prosper in this new environment. During my internship with the AgAID Institute, I worked with Drs. Lee Kalcsits and Paola Pesantes to look into the power of data and how it can help farmers make better-informed decisions on irrigation scheduling, which can lead to more sustainable water use in the future.
I was able to delve into the intriguing world of measuring stem water potential (SWP) in apple tree leaves in the field. Stem water potential gives a clear picture of the tree’s water status, an important indicator of how well hydrated the trees are. To initiate the measurements, my teammates and I would venture out early in the morning, equipped with foil-laminate bags. These sacks played a crucial role in isolating specific leaves from their surrounding environment, allowing us to acquire precise measurements. After carefully placing the bags over selected leaves from two different cultivars, we began a two-hour waiting period to allow the leaf to equilibrate with the vine. The stem water potential of each leaf was then meticulously measured.
Apple orchard managers have traditionally depended on preset irrigation plans, watering their plants at planned times without knowing their actual water needs. They might, for example, water their apple trees every three days, regardless of the weather or the trees’ present water state. Because the irrigation schedule may not exactly match the true water requirements of the fruit trees, this strategy may result in under-watering or over-watering. However, measuring stem water potential in apple tree leaves results in a more informed and accurate approach to irrigation management, since it is a direct measure of the tree’s water condition and hydration needs.
Farmers can gain significant real-time
insights into their trees’ water consumption by frequently monitoring SWP data from their apple orchards. For example, during hot and dry conditions, SWP readings may suggest that the trees are stressed and demand more frequent and deeper watering. In cooler and wetter situations, however, the SWP data may suggest that the trees have enough water, allowing farmers to change their irrigation schedules accordingly. Furthermore, SWP data can help farmers meet more subtle irrigation goals like controlling tree vigor or limiting excessive fruit growth rates. A transition from traditional fixed-schedule irrigation to SWP-based irrigation has significant advantages for apple orchards. It not only helps growers optimize water consumption, but it can also encourage better tree development and increase fruit quality. Furthermore, this more efficient strategy can reduce environmental impacts and improve overall orchard resilience.
Weather data, including current predictions and historical climate records, provide insights on both short-term and long-term atmospheric conditions. Farmers may anticipate dry spells or periods of abundant rainfall, which have an impact on the water requirements of their apple trees, by staying up to date on weather forecasts. SWP data, on the other hand, gives an on-the-ground evaluation of each tree’s specific hydration requirements. SWP data, as the trees’ internal sensor of water stress, provide real-time information on how much water the trees require at any particular time.
Farmers obtain a thorough view of their orchard’s water demands when these two data streams are merged. This synergy between meteorological data (that is indicative of evapotranspiration rates) and SWP data (that reveals how much water the trees lose through transpiration relative to their supply) enables farmers to fine-tune their irrigation plans with pinpoint accuracy. Farmers may proactively change their irrigation programs in cases when weather projections anticipate a lack of rain and SWP data indicates the trees are facing water stress, ensuring their apple trees receive the essential hydration to flourish. If the forecast predicts rain and SWP data reveals that the trees are well-hydrated, farmers may choose to minimize irrigation, conserving water.
While data-driven decision making has great promise, various challenges must be overcome. Farmers may face problems such as restricted access to technology, data security concerns, and the need for technical expertise. For example, farmers may not have the funding or capacity to invest in and actively use sensors to measure SWP; or may not have the expertise using these devices to effectively and efficiently collect the necessary data. In addition, farmers may be unwilling to share their data with others in the sector, or with government or nonprofit entities who provide other, complementary data. Regulatory frameworks that effectively protect the safety and security of data while allowing farmers to connect their data to others may be needed before they are able to get the most out of their data.
Data-driven decision-making can help overcome some of the uncertainties connected with climate change. Farmers may optimize their irrigation schedule and water management by harnessing data, such as stem water potential and meteorological data. However, it is critical to recognize that agriculture is influenced by a variety of elements, including pests, diseases, market pricing, and labor availability, all of which affect productivity, profitability and sustainability. As a result, we must approach data-driven methods with humility, acknowledging that, while data may considerably improve decision-making, it is critical to examine the larger context of agricultural management.
This internship is supported by the AI Research Institutes program supported by NSF and USDA-NIFA under the AI Institute: Agricultural AI for Transforming Workforce and Decision Support (AgAID) award No. 2021-67021-35344.