Proceedings
Authors
| Filter results4 paper(s) found. |
|---|
1. Sidedress N applications for corn based on corn colorNitrogen-deficient corn reflects more light over the entire visible spectrum than nitrogen-suff icient corn. Our objective was to calibrate the relationship between remotely-sensed corn color and the nitrogen need of the corn. Corn color measurements were made two ways: Aerial photographs In-field spectral radiometer A successful calibration would allow: Variable-rate sidedress nitrogen applications that precisely meet the needs of the crop. Precise response to in-season N loss (Figure 1). Data reported... |
2. Field Scale Evaluation of Innovative N Management Systems for CornPrevious research has shown that N fertilizer need for corn can vary widely, both between fields and within fields. Producers, however, almost always apply the same N fertilizer rate to whole fields, and vary N fertilizer rates minimally if at all over whole farms. Matching N fertilizer rates more closely to N needs could produce both economic and environmental benefits. Our objective is to test a range of innovative N management systems for their ability to match N rate recommendations to N needs... |
3. Comparison of Congranulated Fertilizer to Blends with S and Zn in Corn and SoybeansHigh yielding corn and soybean production systems in Missouri have renewed an interest in micronutrient management such as sulfur (S) which is essential for protein formation and zinc. (Zn) which is important for enzymes and metabolic reactions. Yield increases due to sulfur applications are more likely to occur during cool, wet springs when mineralization and crop growth are slow as a result of a decrease in atmospheric sulfur deposition. Soil tests in 2010 indicated that over 60% of the samples... M. Caldwell, K. Nelson, B. Burdick |
4. Improving Digital Soil Maps for Site-specific Soil Fertility Management Using Feature SelectionDigital soil mapping (DSM) has become an attractive option to manage site-specific soil fertility management thanks to its capabilities of creating highly accurate, fine-resolution (e.g., 3 m) soil maps with uncertainty measures associated with soil property predictions. One approach to making soil maps with geospatial technologies is to build statistical models using machine learning (ML) based on the relationships between environmental covariates (e.g., digital terrain attributes, satellite,... C. Ferhatoglu, B.A. Miller |