Next Article in Journal
Geomorphic Evolution of Radial Sand Ridges in the South Yellow Sea Observed from Satellites
Next Article in Special Issue
Radiative Transfer Image Simulation Using L-System Modeled Strawberry Canopies
Previous Article in Journal
Hyperspectral Reflectance Characteristics of Rice Canopies under Changes in Diffuse Radiation Fraction
Previous Article in Special Issue
Integrating Sentinel-1/2 Data and Machine Learning to Map Cotton Fields in Northern Xinjiang, China
 
 
Article

Classification of Daily Crop Phenology in PhenoCams Using Deep Learning and Hidden Markov Models

1
US Department of Agriculture, Agricultural Research Service, Jornada Experimental Range, New Mexico State University, Las Cruces, NM 88003, USA
2
Oak Ridge Institute for Science and Education (ORISE), Oak Ridge, TN 37830, USA
*
Author to whom correspondence should be addressed.
Academic Editor: Jianxi Huang
Remote Sens. 2022, 14(2), 286; https://doi.org/10.3390/rs14020286
Received: 29 October 2021 / Revised: 4 January 2022 / Accepted: 4 January 2022 / Published: 9 January 2022
(This article belongs to the Special Issue Advances in Remote Sensing for Crop Monitoring and Yield Estimation)
Near-surface cameras, such as those in the PhenoCam network, are a common source of ground truth data in modelling and remote sensing studies. Despite having locations across numerous agricultural sites, few studies have used near-surface cameras to track the unique phenology of croplands. Due to management activities, crops do not have a natural vegetation cycle which many phenological extraction methods are based on. For example, a field may experience abrupt changes due to harvesting and tillage throughout the year. A single camera can also record several different plants due to crop rotations, fallow fields, and cover crops. Current methods to estimate phenology metrics from image time series compress all image information into a relative greenness metric, which discards a large amount of contextual information. This can include the type of crop present, whether snow or water is present on the field, the crop phenology, or whether a field lacking green plants consists of bare soil, fully senesced plants, or plant residue. Here, we developed a modelling workflow to create a daily time series of crop type and phenology, while also accounting for other factors such as obstructed images and snow covered fields. We used a mainstream deep learning image classification model, VGG16. Deep learning classification models do not have a temporal component, so to account for temporal correlation among images, our workflow incorporates a hidden Markov model in the post-processing. The initial image classification model had out of sample F1 scores of 0.83–0.85, which improved to 0.86–0.91 after all post-processing steps. The resulting time series show the progression of crops from emergence to harvest, and can serve as a daily, local-scale dataset of field states and phenological stages for agricultural research. View Full-Text
Keywords: crop phenology; PhenoCam; VGG16; hidden Markov model; time series; LTAR crop phenology; PhenoCam; VGG16; hidden Markov model; time series; LTAR
Show Figures

Graphical abstract

MDPI and ACS Style

Taylor, S.D.; Browning, D.M. Classification of Daily Crop Phenology in PhenoCams Using Deep Learning and Hidden Markov Models. Remote Sens. 2022, 14, 286. https://doi.org/10.3390/rs14020286

AMA Style

Taylor SD, Browning DM. Classification of Daily Crop Phenology in PhenoCams Using Deep Learning and Hidden Markov Models. Remote Sensing. 2022; 14(2):286. https://doi.org/10.3390/rs14020286

Chicago/Turabian Style

Taylor, Shawn D., and Dawn M. Browning. 2022. "Classification of Daily Crop Phenology in PhenoCams Using Deep Learning and Hidden Markov Models" Remote Sensing 14, no. 2: 286. https://doi.org/10.3390/rs14020286

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop