Crop yield prediction from multi-spectral, multi-temporal remotely sensed imagery using recurrent 3D convolutional neural networks

Qiao, Mengjia; He, Xiaohui; Cheng, Xijie; Li, Panle; Luo, Haotian; Zhang, Lehan; Tian, Zengshan

doi:10.1016/j.jag.2021.102436

Cited by 37 publications

(11 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, many studies have used only spectral data from single-period images to predict SOM, which limits the accuracy of the estimation models [58]. The introduction of temporal information compensates for the lack of information in single-temporal images and allows a more comprehensive extraction of pixel information common to multiple images [59]. Additionally, multitemporal images can also be characterized by the constructed multitemporal spectral indices to characterize the interactivity of the factors, which can achieve the goal of reducing the effect of the factors and thus improve the accuracy of SOM estimation models [54].…”

Section: Discussionmentioning

confidence: 99%

Combining Multitemporal Sentinel-2A Spectral Imaging and Random Forest to Improve the Accuracy of Soil Organic Matter Estimates in the Plough Layer for Cultivated Land

Wang

Yong

2022

Agriculture

View full text Add to dashboard Cite

Soil organic matter (SOM) is vital for assessing the quality of arable land. A fast and reliable estimation of SOM is important to predict the soil carbon stock in cropland. In this study, we aimed to explore the potential of combining multitemporal Sentinel-2A imagery and random forest (RF) to improve the accuracy of SOM estimates in the plough layer for cultivated land at a regional scale. The field data of SOM content were utilized along with multitemporal Sentinel-2A images acquired over three years during the bare soil period to develop spectral indices. The best bands and spectral indices were selected as prediction variables by using the RF algorithm. Partial least squares (PLS), geographically weighted regression (GWR), and RF were employed to calibrate spectral indices for the SOM content, and the optimal calibration model was used for the mapping of the SOM content in arable land at a regional scale. The results showed the following. (1) The multitemporal image estimation model outperformed the single-temporal image estimation model. The estimation model that utilized the optimal bands and spectral indices as prediction variables usually had better accuracy than the models based on full spectral data. (2) For the SOM content estimates, the performance was better with RF than with PLS and GWR in almost all cases. (3) The most accurate SOM estimation in the case area was achieved by using multitemporal images from 2018 and the RF calibration model based on the optimal bands and spectral indices as prediction variables, with R2val (coefficient of determination of the validation data set) = 0.67, RMSEval (root mean square error of the validation dataset) = 2.05, and RPIQval(ratio of performance to interquartile range of the validation dataset) = 3.36. (4) The estimated SOM content in the plough layer for cultivated land throughout the study area ranged from 16.17 to 36.98 g kg−1 and exhibited an increasing trend from north to south. In the current study, we developed a framework that combines multitemporal remote sensing imagery and RF for the SOM estimation, which can improve the accuracy of quantitative SOM estimations, provide a dynamic, rapid, and low-cost technique for understanding soil fertility, and offer an early warning of changes in soil quality.

show abstract

Section: Discussionmentioning

confidence: 99%

Combining Multitemporal Sentinel-2A Spectral Imaging and Random Forest to Improve the Accuracy of Soil Organic Matter Estimates in the Plough Layer for Cultivated Land

Wang

Yong

2022

Agriculture

View full text Add to dashboard Cite

show abstract

“…The use of spectral reflectance for predicting crop yield has been extensively investigated. For example, Qiao et al (2021) reported the efficiency of using long-time series multi-spectral images for yield mapping of different crop species using an automated spatial-spectral feature extractor. The application of hyperspectral reflectance in predicting the wheat grain yield was studied by Fei et al (2021) , who reported the effectiveness of red and NIR regions in predicting the grain yield in different irrigation regimes.…”

Section: Discussionmentioning

confidence: 99%

Genome-Wide Association Studies of Soybean Yield-Related Hyperspectral Reflectance Bands Using Machine Learning-Mediated Data Integration Methods

Yoosefzadeh-Najafabadi

Torabi

Tulpan

et al. 2021

Front. Plant Sci.

View full text Add to dashboard Cite

In conjunction with big data analysis methods, plant omics technologies have provided scientists with cost-effective and promising tools for discovering genetic architectures of complex agronomic traits using large breeding populations. In recent years, there has been significant progress in plant phenomics and genomics approaches for generating reliable large datasets. However, selecting an appropriate data integration and analysis method to improve the efficiency of phenome-phenome and phenome-genome association studies is still a bottleneck. This study proposes a hyperspectral wide association study (HypWAS) approach as a phenome-phenome association analysis through a hierarchical data integration strategy to estimate the prediction power of hyperspectral reflectance bands in predicting soybean seed yield. Using HypWAS, five important hyperspectral reflectance bands in visible, red-edge, and near-infrared regions were identified significantly associated with seed yield. The phenome-genome association analysis of each tested hyperspectral reflectance band was performed using two conventional genome-wide association studies (GWAS) methods and a machine learning mediated GWAS based on the support vector regression (SVR) method. Using SVR-mediated GWAS, more relevant QTL with the physiological background of the tested hyperspectral reflectance bands were detected, supported by the functional annotation of candidate gene analyses. The results of this study have indicated the advantages of using hierarchical data integration strategy and advanced mathematical methods coupled with phenome-phenome and phenome-genome association analyses for a better understanding of the biology and genetic backgrounds of hyperspectral reflectance bands affecting soybean yield formation. The identified yield-related hyperspectral reflectance bands using HypWAS can be used as indirect selection criteria for selecting superior genotypes with improved yield genetic gains in large breeding populations.

show abstract

“…This is because the highest correlation is shown on this date. In addition, most previous studies suggested that the best date for taking images to predict grain yield is about one to two months before the start of harvest (Li et al, 2021).…”

Section: Landsat 8 Oli and Sentinel-2a Satellite Image Datamentioning

confidence: 99%

“…Thus the appearance of digital technology and smart agriculture were among the important factors in enhancing the surveillance of agriculture, the production of cereal and its estimation (Khalil & Abdullaev, 2021). In these recent years, with the advancement of remote sensing technology, it has been easier to predict the yield of cereals, by way of the differentiating the location, temporal, and brightness data all around the world, to an acceptable degree (Qiao et al, 2021). The notes from remote sensing shed light on some of the changes that relate to the earth, soil, plant cover and the difference between plant health (Kamilaris et al, 2017b).…”

mentioning

confidence: 99%

Sentinel‐2 Accurately Estimated Wheat Yield in a Semi-arid Region Compared With Landsat‐8

Ibrahim¹,

Rasul²,

Abdullah³

2022

Preprint

View full text Add to dashboard Cite

Wheat and barley are among the primary food resources of the world population; therefore, their growth and observation are essential in farms to enhance food security worldwide. On top of that, careful observation of the product is essential to find solutions for the issues faced during their production and to reduce the impacts of weather changes. With the advancement of Remote Sensing technology, the observation and estimation process has increased. In this study, numbers of spectral vegetation indices was used along with canopy biophysical properties ( LAI ) and biochemical properties (chlorophyll), there calculated from (Landsat 8 and Sentinel-2) satellite data. The wheat and barley samples were collected before were be ready for harvest, and a relation with the vegetarian indices was established using the Multi-Linear Regression module, in which the equations used in predicting the harvest were developed and used to create a graph for expected harvest. The result indicated that there is a strong relationship between the vegetation indices of Sentinel-2 and Landsat images and the actual grain yield with R2 of 0.77 and 0.71, respectively. The results show that the strongest correlation is observed between the LAI data obtained from Sentinel data and cereal yield data, with an R2 0.68, and the highest correlation for the indices of Landsat images is observed in the NDWI with R2 0.59 and the lowest degree of error was in the root mean square error (RMSE) for the Sentinel-2 and Landsat 8 with 0.57 and 1.54. In addition, this study also showed that the least relationship for grain yield prediction was observed between the NDRI for Sentinel-2 (R2 0.1) and SAVI for Landsat image (R2 0.47).

show abstract

Crop yield prediction from multi-spectral, multi-temporal remotely sensed imagery using recurrent 3D convolutional neural networks

Cited by 37 publications

References 39 publications

Combining Multitemporal Sentinel-2A Spectral Imaging and Random Forest to Improve the Accuracy of Soil Organic Matter Estimates in the Plough Layer for Cultivated Land

Combining Multitemporal Sentinel-2A Spectral Imaging and Random Forest to Improve the Accuracy of Soil Organic Matter Estimates in the Plough Layer for Cultivated Land

Genome-Wide Association Studies of Soybean Yield-Related Hyperspectral Reflectance Bands Using Machine Learning-Mediated Data Integration Methods

Sentinel‐2 Accurately Estimated Wheat Yield in a Semi-arid Region Compared With Landsat‐8

Contact Info

Product

Resources

About