Near real-time detection and forecasting of within-field phenology of winter wheat and corn using Sentinel-2 time-series data

Liao, Chunhua; Wang, Jinfei; Shan, Bo; Shang, Jiali; Dong, Taifeng; He, Yongjun

doi:10.1016/j.isprsjprs.2022.12.025

Cited by 19 publications

(10 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, single remote-sensing images often fail to precisely reflect complex ground features due to multiple factors. Optical images, affected by elements such as spectral resolution and spatial resolution, often lead to phenomena like spectral confusion and variability [12]. Even though Synthetic Aperture Radar (SAR) data provide the benefits of all-weather, all-day operability, and immunity to cloudy and rainy conditions, they can be easily compromised by speckle noise interference [13].…”

Section: Introductionmentioning

confidence: 99%

Eucalyptus Plantation Area Extraction Based on SLPSO-RFE Feature Selection and Multi-Temporal Sentinel-1/2 Data

Lin,

Ren,

et al. 2023

Forests

View full text Add to dashboard Cite

An accurate and efficient estimation of eucalyptus plantation areas is of paramount significance for forestry resource management and ecological environment monitoring. Currently, combining multidimensional optical and SAR images with machine learning has become an important method for eucalyptus plantation classification, but there are still some challenges in feature selection. This study proposes a feature selection method that combines multi-temporal Sentinel-1 and Sentinel-2 data with SLPSO (social learning particle swarm optimization) and RFE (Recursive Feature Elimination), which reduces the impact of information redundancy and improves classification accuracy. Specifically, this paper first fuses multi-temporal Sentinel-1 and Sentinel-2 data, and then carries out feature selection by combining SLPSO and RFE to mitigate the effects of information redundancy. Next, based on features such as the spectrum, red-edge indices, texture characteristics, vegetation indices, and backscatter coefficients, the study employs the Simple Non-Iterative Clustering (SNIC) object-oriented method and three different types of machine-learning models: Random Forest (RF), Classification and Regression Trees (CART), and Support Vector Machines (SVM) for the extraction of eucalyptus plantation areas. Each model uses a supervised-learning method, with labeled training data guiding the classification of eucalyptus plantation regions. Lastly, to validate the efficacy of selecting multi-temporal data and the performance of the SLPSO–RFE model in classification, a comparative analysis is undertaken against the classification results derived from single-temporal data and the ReliefF–RFE feature selection scheme. The findings reveal that employing SLPSO–RFE for feature selection significantly elevates the classification precision of eucalyptus plantations across all three classifiers. The overall accuracy rates were noted at 95.48% for SVM, 96% for CART, and 97.97% for RF. When contrasted with classification outcomes from multi-temporal data and ReliefF–RFE, the overall accuracy for the trio of models saw an increase of 10%, 8%, and 8.54%, respectively. The accuracy enhancement was even more pronounced when juxtaposed with results from single-temporal data and ReliefF-RFE, at increments of 15.25%, 13.58%, and 14.54% respectively. The insights from this research carry profound theoretical implications and practical applications, particularly in identifying and extracting eucalyptus plantations leveraging multi-temporal data and feature selection.

show abstract

Section: Introductionmentioning

confidence: 99%

Eucalyptus Plantation Area Extraction Based on SLPSO-RFE Feature Selection and Multi-Temporal Sentinel-1/2 Data

Lin,

Ren,

et al. 2023

Forests

View full text Add to dashboard Cite

show abstract

“…Current NRT crop phenology identification techniques pose implementation challenges when applied at the sub-field scale using available high spatial resolution satellite datasets with a low temporal resolution. Moreover, these methods are restricted to estimating particular phenological events from a remote sensing perspective, which contrasts with the scales commonly employed in crop phenology assessment (Liao et al, 2023). Gobin et al (2023) establish a correlation between in-situ field phenological observations and data gathered from proximal and satellite sensors.…”

Section: Introductionmentioning

confidence: 99%

“…Even when they deduce the phenological stages of crops within the growing season, they conclude that higher spatiotemporal resolution data and supplementary spectral information would enhance the identification of crop phenology to support crop performance and yield monitoring. Liao et al (2023) proposed an NRT methodology for detecting and forecasting phenology in winter wheat and corn using timely available Sentinel-2 data during the growing season in Canada. It integrated both the shape model-fitting approach and the canopy structure dynamics model to describe the crop's growth and development (Liao et al, 2019).…”

Section: Introductionmentioning

confidence: 99%

Near real-time soybean phenology detection using proximally-sensed hyperspectral canopy reflectance and machine learning methods

Rigalli,

Bulacio,

Romagnoli

et al. 2024

Preprint

View full text Add to dashboard Cite

To date, most of the research data on the selection of plant types based on crop growth phenology is obtained by expert observations in the field. The extraction of soybean phenology stages/phases from canopy spectral data might provide timing information for optimal field management. In this work a simple high-resolution technique for collecting proximally-sensed hyperspectral data at canopy level was performed and machine learning phenology models based on canopy spectral data plus physical predictors were developed. An empirical study of the effects of parameterization of the machine learning models with physical ancillary predictors is conducted, estimating soybean phenology in datasets collected in a-posteriori time than the interval where the training data were gathered. The accuracy achieved for reproductive single stages from the beginning of seed development to full maturity was 84%, when these stages were grouped into phases, the detection accuracy reached 92%. The ability to identify soybean phe-nology in near real-time allows extrapolation of this study to a regional scale by employing UAVs outfitted with the same instruments used in this work.

show abstract

“…However, satellite data are effective tools for monitoring land surfaces at large spatial and suitable temporal scales, which allow tracking of the phenological dynamics of vegetation over large areas [11]. The phenology obtained from satellite data is usually determined from vegetation indices (VIs), such as the normalized difference vegetation index (NDVI) or the enhanced vegetation index (EVI) [11][12][13].…”

Section: Introductionmentioning

confidence: 99%

Recent Cereal Phenological Variations under Mediterranean Conditions

Benito-Verdugo,

González-Zamora,

Martínez-Fernández

2024

Remote Sensing

View full text Add to dashboard Cite

This study analyzes the temporal patterns of rainfed cereal phenology extracted from the GIMMS NDVI3g dataset in the main cereal-growing regions under a Mediterranean climate in Spain, Portugal, France and Italy during the period 1982–2022. The series before and after the beginning of the 21st century were analyzed separately. Phenological parameters were extracted using the modified dynamic threshold method, and their trends were analyzed. Correlation analyses were performed to study the relationships among these parameters and to analyze the influence of hydroclimatic variables on the start (SOS) and end (EOS) of the growing season. Results showed a temporal reversal in phenological trends between both study periods, coinciding with the global warming hiatus. In the first period (1982–2002), SOS and EOS advanced (−7.5 and −3.1 days, respectively), and the length of growing season (LOS) increased. However, during the second stage (2003–2022), SOS and EOS were delayed (7.5 and 1.7 days, respectively), and LOS decreased. Similar dynamics were observed for the influence of the hydroclimatic variables on SOS and EOS, stronger in the first period and weaker in the second. This study provides valuable information on the phenological dynamics of rainfed cereals that may be useful for their management and planning in climate change scenarios.

show abstract

Near real-time detection and forecasting of within-field phenology of winter wheat and corn using Sentinel-2 time-series data

Cited by 19 publications

References 47 publications

Eucalyptus Plantation Area Extraction Based on SLPSO-RFE Feature Selection and Multi-Temporal Sentinel-1/2 Data

Eucalyptus Plantation Area Extraction Based on SLPSO-RFE Feature Selection and Multi-Temporal Sentinel-1/2 Data

Near real-time soybean phenology detection using proximally-sensed hyperspectral canopy reflectance and machine learning methods

Recent Cereal Phenological Variations under Mediterranean Conditions

Contact Info

Product

Resources

About