Reverse N lookup, sensor based N rates using Weather improved INSEY Nicole Remondet Rationale Weather is an aspect of agricultural sciences that cannot be controlled and it has a huge impact on the growth of plants. In the past the reliability of weather predictions have been relatively questionable. “The Oklahoma Mesonet is a world-class network of environmental monitoring stations. The Oklahoma Mesonet consists of 120 automated stations covering Oklahoma. At each site, the environment is measured by a set of instruments located on or near a 10-meter-tall tower” (Mesonet) with the vast amounts of data it is important for us as agriculturalists to use this information to our advantage.“The current model utilized for predicting grain yield potential was that described by Raun et al. (2005). The INSEY was calculated by dividing the NDVI by the cumulative number of GDD with a growing threshold value of 4.4ºC. A non-linear relationship was established between INSEY and final grain yield, and the equation from this relationship is thus used to predict yield” (Jacob T. Bushong. Et al.) “NITROGEN is well documented as a limiting nutrient in crop production and is considered one of the best producer inputs to increase profitability under an appropriate management system” (R.K. Teal et al.). So because of this it is useful to continue to evaluate the INSEY to make it more accurate so that fertilizer resources are not wasted. Objectives One objective of this study is to develop a model that incorporates climatic parameters with NDVI measurements to increase the reliability of predicting wheat grain yield in-season. Using current and long term data, the current INSEY will be evaluated from five locations: Lake Carl Blackwell, Lahoma, Hennessey, Perkins, and Efaw. Another objective of this study is to compare the weather improved model with the current model. Methods NDVI Data and yield data will be collected from current trials then documented with previous data. First a yield prediction model will be created through the creation of various graphs, and then using a statistical program such as SAS to evaluate the significance of the relationships between different aspects of data. This could be done by comparing “The maximized adjusted R 2 values, to determine the appropriate regression equation parameters that will best estimate final grain yield” (Jacob Bushog et al). After this has been accomplished the new predicted yields will be compared to the predicted yield of the previous yield calculator as well as including the actual yield that was detected at harvest. Conclusion While the current yield predictor is efficient there is always a way to improve it by using accurate weather information in association with the yield estimation. The aspects of weather that one could include could be: cumulative Growing Degree Days, changing the maximum/minimum temperature utilized, or by altering the methods of calculating GDD. Using resources such as the Mesonet the weather information one can utilize will be accurate. Using less resources to grow our crops will be increasingly important in the coming years as the human population grows and the resources available begin to dwindle. Since weather has such a huge impact on the growth of crops it will be beneficial to incorporate such data into the current INSEY so that less resources could be used. From Jake Bushog’s previous paper where he incorporated soil moisture into his yield calculator. Linear regression of measured grain yield of plots with no mid-season N fertilizer with estimates of yield potential without added N derived from the Current N Fertilizer Optimization Algorithm (Left) and the Proposed N Fertilizer Optimization Algorithm (Right ). Works Cited: Development of an In-season Estimate of Yield Potential Utilizing Optical Crop Sensors and Soil Moisture Data for Winter Wheat,Jacob T. Bushong *1, Jeremiah L. Mullock 1, Eric C. Miller 1, William R. Raun 1, Arthur R. Klatt 1, and D. Brian Arnall 1 In-Season Prediction of Corn Grain Yield Potential Using Normalized Difference Vegetation Index R. K. Teal, B. Tubana, K. Girma, K. W. Freeman, D. B. Arnall, O. Walsh, and W. R. Raun*