Function fitting for modeling seasonal normalized difference vegetation index time series and early forecasting of soybean yield

Dubrovin, Konstantin; Сорокин, А. А.

doi:10.1016/j.cj.2021.12.013

Cited by 7 publications

(2 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It can be observed that the soybean NDVI plots showed a single peak and that employing simple functions with a single extremum may be better suited to fit such series (similar to the Gaussian function) [24,43]. However, single-peak functions were less effective for fitting the NDVI series for perennial grasses and buckwheat (when sown in July), which have two peaks [44]. In practice, unmarked data (where the crop was not known) were used when using the classifier.…”

Section: Ndvi Time Series Restorationmentioning

confidence: 99%

Multi-Year Cropland Mapping Based on Remote Sensing Data: A Case Study for the Khabarovsk Territory, Russia

Dubrovin,

Verkhoturov,

Stepanov

et al. 2024

Remote Sensing

Self Cite

View full text Add to dashboard Cite

Cropland mapping using remote sensing data is the basis for effective crop monitoring, crop rotation control, and the detection of irrational land use. Classification using Normalized Difference Vegetation Index (NDVI) time series from multi-year data requires additional time costs, especially when sentinel data are sparse. Approximation by nonlinear functions was proposed to solve this problem. Time series of weekly NDVI composites were plotted using multispectral Sentinel-2 (Level-2A) images at a resolution of 10 m for sites in Khabarovsk District from April to October in the years 2021 and 2022. Missing values due to the lack of suitable images for analysis were recovered using cubic polynomial, Fourier series, and double sinusoidal function approximation. The classes that were considered included crops, namely, soybean, buckwheat, oat, and perennial grasses, and fallow. The mean absolute percentage error (MAPE) of each class fitting was calculated. It was found that Fourier series fitting showed the highest accuracy, with a mean error of 8.2%. Different classifiers, such as the support vector machine (SVM), random forest (RF), and gradient boosting (GB), were comparatively evaluated. The overall accuracy (OA) for the site pixels during the cross-validation (Fourier series restored) was 67.3%, 87.2%, and 85.9% for the SVM, RF, and GB classifiers, respectively. Thus, it was established that the best result in terms of combined accuracy, performance, and limitations in cropland mapping was achieved by composite construction using Fourier series and machine learning using GB. Similar results should be expected in regions with similar cropland structures and crop phenological cycles, including other regions of the Far East.

show abstract

Section: Ndvi Time Series Restorationmentioning

confidence: 99%

Multi-Year Cropland Mapping Based on Remote Sensing Data: A Case Study for the Khabarovsk Territory, Russia

Dubrovin,

Verkhoturov,

Stepanov

et al. 2024

Remote Sensing

Self Cite

View full text Add to dashboard Cite

show abstract

“…Therefore, understanding light interception and leaf area growth during the soybean development cycle under reduced SR will aid in identifying genetic and environmental strategies for reducing the optimal SR without changing the yield. Variables such as LAI, soil cover by plants (Purcell, 2000), and vegetation indices such as the Normalized Difference Vegetation Index (NDVI) (Stepanov et al, 2022) have been used to assess solar interception by the canopy. Of these variables, NDVI can be obtained more quickly, on a large scale, provided the necessary equipment or access to satellite images with the adequate resolution is available (Roznik et al, 2022).…”

Section: Introductionmentioning

confidence: 99%

Leaf area index and light interception relationship with seed yield of indeterminate soybean cultivars under reduced seeding rates

Ferreira

Zucareli

Zeffa

et al. 2023

Preprint

View full text Add to dashboard Cite

Owing to the recent increase in the cost of germplasm, transgenic royalties, and seed treatments, studies have been conducted to analyze the capacity of modern cultivars to maintain yield under reduced seeding rates (SR). This study elucidated the effect of reduced SR on the evolution of leaf area index (LAI) and light interception by the canopy of soybean cultivars with contrasting branching plasticity and identified the association of these variables with seed yield. Field experiments were conducted in randomized blocks using BRS 1010IPRO (high plasticity) and NS 5959IPRO (medium plasticity) cultivars, with five SRs: 100, 80, 60, 40, and 20% of the recommended SR. The SR reduction did not reduce the seed yield to the point where the LAI and light interception in the reproductive phase were similar to those obtained with the recommended seeding rate. Higher LAI and light interception confer greater potential for reducing the seeding rate in cultivars with higher branching plasticity. The minimum optimal SR (MOSR) for cumulative LAI, Normalized Difference Vegetation Index (NDVI), and intercepted photosynthetic active radiation (IPAR) in the reproductive phase was closer to the MOSR for seed yield than in the vegetative phase or the total crop cycle, indicating “luxury growth” in the vegetative phase at the recommended SRs. Cumulative LAI, NDVI, and IPAR in the reproductive phase had a greater correlation with seed yield than those in the vegetative phase or the total crop cycle. The cumulative NDVI had a higher correlation with seed yield than cumulative LAI and IPAR.

show abstract

Crop phenotyping studies with application to crop monitoring

et al. 2022

View full text Add to dashboard Cite

Function fitting for modeling seasonal normalized difference vegetation index time series and early forecasting of soybean yield

Cited by 7 publications

References 26 publications

Multi-Year Cropland Mapping Based on Remote Sensing Data: A Case Study for the Khabarovsk Territory, Russia

Multi-Year Cropland Mapping Based on Remote Sensing Data: A Case Study for the Khabarovsk Territory, Russia

Leaf area index and light interception relationship with seed yield of indeterminate soybean cultivars under reduced seeding rates

Crop phenotyping studies with application to crop monitoring

Contact Info

Product

Resources

About