An official website of the United States government
For farmers, policymakers, and government agencies, it is critical to accurately define agricultural crop phenology and its spatial-temporal variability. At the moment, two approaches are utilized to report crop phenology. On one hand, land surface phenology provides information about the overall trend, whereas weekly reports from USDA-NASS provide information about the development of particular crops at the regional level. High-cadence earth observations might help to improve the accuracy of these estimations and bring more precise crop phenology classifications closer to what farmers demand. The second component of the proposed solution requires the use of robust classifiers (e.g., random forest, RF) capable of successfully managing large data sets. To evaluate this solution, this study compared the output of a RF classifier model using weather, two different satellite sources (Planet Fusion; PF and Sentinel-2; S-2), and ground truth data to improve maize (Zea mays L.) crop phenology classification using two regions of Kansas (Southwest and Central) as a testbed during the 2017 growing season. Our findings suggests that high temporal resolution (PF) data can significantly improve crop classification metrics (f1-score = 0.94) relative to S-2 (f1-score = 0.86). Additionally, a decline in the f1-score between 0.74 and 0.60 was obtained when we assessed the ability of S-2 to extend the temporal forecast for crop phenology. This research highlights the critical nature of very high temporal resolution (daily) earth observation data for crop monitoring and decision making in agriculture.
more »
« less
This content will become publicly available on January 1, 2026
Remote Sensing Based Crop Monitoring Techniques: A Case Study for the Navajo Nation
Abstract. Agriculture plays a major role in eradicating poverty, promoting prosperity, and nourishing a projected 10 billion people by 2050 globally. In a changing climate, achieving optimal agricultural yields requires a deeper understanding of available natural resources and crops. This is especially important for places like the Navajo Nation, which faces significant challenges in food supply chain management due to various factors such as water demand, water quality, and insufficient information about land fertility and crops timings/seasons. Additionally, it is the largest Native American reservation in the U.S. It covers 27,425 square miles across Arizona, Utah, and New Mexico and has a population of 165,158 people, according to the 2020 census. Agriculture has been a key part of life in the Navajo Nation since the late 19th and early 20th centuries, playing a big role in the region’s development and stability. However, the lack of knowledge about decisions and actions during the crop growing season has resulted in lower crop productivity, as evidenced by the USDA statistical report for the Navajo Nation in 2012 and 2017. To support farmers by providing better decision-making and actionable insights, high-resolution, open-source Sentinel-2 satellite images are being used to develop advanced crop mapping techniques for identifying the spatial extent of various agricultural crops in the Navajo Nation. To address this, a collection of research papers was reviewed, leading to the development of a new methodology for analysing Sentinel-2 data from the 2017 and 2023 growing seasons within the Navajo Nation. The collected data was pre-processed by creating monthly median composites of surface reflectance to remove noise and enhance the results more accurately. After preprocessing, spectral indices were calculated from the spectral bands, including NDVI (Normalized Difference Vegetation Index), EVI (Enhanced Vegetation Index), GCVI (Green Chlorophyll Vegetation Index), and LSWI (Land Surface Water Index), to differentiate the crops more precisely. The training datasets were obtained from the USDA’s Crop Data Layer (CDL) and split into 80% for training and 20% for validating the Random Forest supervised classification algorithm. The classification resulted in an accuracy of 80%. Finally, the accuracy of the results was compared with independent ground truth data. This research identifies notable discrepancies between the CDL data and the Navajo Nation agricultural census statistical report, particularly in estimating corn acreage for the Chinle and Fort Defiance agencies. Ultimately this approach information is used to provide actionable insights to Navajo Nation farmers.
more »
« less
- Award ID(s):
- 2318706
- PAR ID:
- 10636330
- Publisher / Repository:
- ISPRS
- Date Published:
- Journal Name:
- The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
- Volume:
- XLVIII-M-5-2024
- ISSN:
- 2194-9034
- Page Range / eLocation ID:
- 165 to 170
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Mapping and monitoring crops is a key step towards the sustainable intensification of agriculture and addressing global food security. A dataset like ImageNet that revolutionized computer vision applications can accelerate the development of novel crop mapping techniques. Currently, the United States Department of Agriculture (USDA) annually releases the Cropland Data Layer (CDL) which contains crop labels at 30m resolution for the entire United States of America. While CDL is state of the art and is widely used for a number of agricultural applications, it has a number of limitations (e.g., pixelated errors, labels carried over from previous years, and errors in the classification of minor crops). In this work, we create a new semantic segmentation benchmark dataset, which we call CalCROP21, for the diverse crops in the Central Valley region of California at 10m spatial resolution using a Google Earth Engine based robust image processing pipeline and a novel attention-based spatio-temporal semantic segmentation algorithm STATT. STATT uses re-sampled (interpolated) CDL labels for training but is able to generate a better prediction than CDL by leveraging spatial and temporal patterns in Sentinel2 multi-spectral image series to effectively capture phenologic differences amongst crops and uses attention to reduce the impact of clouds and other atmospheric disturbances. We also present a comprehensive evaluation to show that STATT has significantly better results when compared to the resampled CDL labels. We have released the dataset and the processing pipeline code for generating the benchmark dataset.more » « less
-
Data-driven technologies are employed in agriculture to optimize the use of limited resources. Crop evapotranspiration (ET) estimates the actual amount of water that crops require at different growth stages, thereby proving to be the essential information needed for precision irrigation. Crop ET is essential in areas like the US High Plains, where farmers rely on groundwater for irrigation. The sustainability of irrigated agriculture in the region is threatened by diminishing groundwater levels, and the increasing frequency of extreme events caused by climate change further exacerbates the situation. These conditions can significantly affect crop ET rates, leading to water stress, which adversely affects crop yields. In this study, we analyze historical climate data using a machine learning model to determine which of the climate extreme indices most influences crop ET. Crop ET is estimated using reference ET derived from the FAO Penman–Monteith equation, which is multiplied with the crop coefficient data estimated from the remotely sensed normalized difference vegetation index (NDVI). We found that the climate extreme indices of consecutive dry days and the mean weekly maximum temperatures most influenced crop ET. It was found that temperature-derived indices influenced crop ET more than precipitation-derived indices. Under the future climate scenarios, we predict that crop ET will increase by 0.4% and 1.7% in the near term, by 3.1% and 5.9% in the middle term, and by 3.8% and 9.6% at the end of the century under low greenhouse gas emission and high greenhouse gas emission scenarios, respectively. These predicted changes in seasonal crop ET can help agricultural producers to make well-informed decisions to optimize groundwater resources.more » « less
-
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
-
Abstract Efficient, more accurate reporting of maize ( Zea mays L.) phenology, crop condition, and progress is crucial for agronomists and policy makers. Integration of satellite imagery with machine learning models has shown great potential to improve crop classification and facilitate in-season phenological reports. However, crop phenology classification precision must be substantially improved to transform data into actionable management decisions for farmers and agronomists. An integrated approach utilizing ground truth field data for maize crop phenology (2013–2018 seasons), satellite imagery (Landsat 8), and weather data was explored with the following objectives: (i) model training and validation—identify the best combination of spectral bands, vegetation indices (VIs), weather parameters, geolocation, and ground truth data, resulting in a model with the highest accuracy across years at each season segment (step one) and (ii) model testing—post-selection model performance evaluation for each phenology class with unseen data (hold-out cross-validation) (step two). The best model performance for classifying maize phenology was documented when VIs (NDVI, EVI, GCVI, NDWI, GVMI) and vapor pressure deficit (VPD) were used as input variables. This study supports the integration of field ground truth, satellite imagery, and weather data to classify maize crop phenology, thereby facilitating foundational decision making and agricultural interventions for the different members of the agricultural chain.more » « less
