skip to main content

This content will become publicly available on August 1, 2024

Title: CropSow: An integrative remotely sensed crop modeling framework for field-level crop planting date estimation
Award ID(s):
Author(s) / Creator(s):
; ;
Publisher / Repository:
Date Published:
Journal Name:
ISPRS Journal of Photogrammetry and Remote Sensing
Page Range / eLocation ID:
334 to 355
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. null (Ed.)
  2. Crop type information at the field level is vital for many types of research and applications. The United States Department of Agriculture (USDA) provides information on crop types for US cropland as a Cropland Data Layer (CDL). However, CDL is only available at the end of the year after the crop growing season. Therefore, CDL is unable to support in-season research and decision-making regarding crop loss estimation, yield estimation, and grain pricing. The USDA mostly relies on field survey and farmers’ reports for the ground truth to train image classification models, which is one of the major reasons for the delayed release of CDL. This research aims to use trusted pixels as ground truth to train classification models. Trusted pixels are pixels which follow a specific crop rotation pattern. These trusted pixels are used to train image classification models for the classification of in-season Landsat images to identify major crop types. Six different classification algorithms are investigated and tested to select the best algorithm for this study. The Random Forest algorithm stands out among selected algorithms. This study classified Landsat scenes between May and mid-August for Iowa. The overall agreements of classification results with CDL in 2017 are 84%, 94%, and 96% for May, June, and July, respectively. The classification accuracies have been assessed through 683 ground truth data points collected from the fields. The overall accuracies of single date multi-band image classification are 84%, 89% and 92% for May, June, and July, respectively. The result also shows higher accuracy (94–95%) can be achieved through multi-date image classification compared to single date image classification. 
    more » « less
  3. null (Ed.)
  4. GIS data layer on crop field boundary has many applications in agricultural research, ecosystem study, crop monitoring, and land management. Crop field boundary mapping through field survey is not time and cost effective for vast agriculture areas. Onscreen digitization on fine-resolution satellite image is also labor-intensive and error-prone. The recent development in image segmentation based on their spectral characteristics is promising for cropland boundary detection. However, processing of large volume multi-band satellite images often required high-performance computation systems. This study utilized crop rotation information for the delineation of field boundaries. In this study, crop field boundaries of Iowa in the United States are extracted using multi-year (2007-2018) CDL data. The process is simple compared to boundary extraction from multi-date remote sensing data. Although this process was unable to distinguish some adjacent fields, the overall accuracy is promising. Utilization of advanced geoprocessing algorithms and tools on polygon correction may improve the result significantly. Extracted field boundaries are validated by superimposing on fine resolution Google Earth images. The result shows that crop field boundaries can easily be extracted with reasonable accuracy using crop rotation information. 
    more » « less
  5. Abstract Low nitrogen use efficiency (NUE) is ubiquitous in agricultural systems, with mounting global scale consequences for both atmospheric aspects of climate and downstream ecosystems. Since NUE-related soil characteristics such as water holding capacity and organic matter are likely to vary at small scales (< 1 ha), understanding the influence of soil characteristics on NUE at the subfield scale (< 32 ha) could increase fertilizer NUE. Here, we quantify NUE in four conventionally managed dryland winter-wheat fields in Montana following multiple years of sub-field scale variation in experimental N fertilizer applications. To inform farmer decisions that incorporates NUE, we developed a generalizable model to predict subfield scale NUE by comparing six candidate models, using ecological and biogeochemical data gathered from open-source data repositories and from normal farm operations, including yield and protein monitoring data. While NUE varied across fields and years, efficiency was highest in areas of fields with low N availability from both fertilizer and estimated mineralization of soil organic N (SON). At low levels of applied N, distinct responses among fields suggest distinct capacities to supply non-fertilizer plant-available N, suggesting that mineralization supplies more available N in locations with higher total N, reducing efficiency for any applied rate. Comparing modelling approaches, a random forest regression model of NUE provided predictions with the least error relative to observed NUE. Subfield scale predictive models of NUE can help to optimize efficiency in agronomic systems, maximizing both economic net return and NUE, which provides a valuable approach for optimization of nitrogen fertilizer use. 
    more » « less