Unmanned Aerial System (UAS)-based phenotyping of soybean using multi-sensor data fusion and extreme learning machine

Maimaitijiang, Maitiniyazi; Ghulam, Abduwasit; Sidike, Paheding; Hartling, Sean; Maimaitiyiming, Matthew; Peterson, Kyle T.; Shavers, Ethan; Fishman, Jack; Peterson, Jim; Kadam, Suhas; Burken, Joel G.; Fritschi, Felix B.

doi:10.1016/j.isprsjprs.2017.10.011

Cited by 300 publications

(212 citation statements)

References 125 publications

Supporting

Mentioning

199

Contrasting

Unclassified

Order By: Relevance

“…A typical ELM is a form of the FFNN that contains an input layer, a single hidden layer, and one output layer. In recent remote sensing studies, ELM has been found to surpass widespread methods such as partial least squares (PLS) and support vector machine (SVM), producing high predictive power while consuming significantly less computational time when dealing with complex spectral interactions [42,43]. ELM gains advantages over other FFNN approaches as the weights of the hidden layer within ELM can be randomly produced and updated without iterative optimization [44].…”

Section: Regression Modelingmentioning

confidence: 99%

See 1 more Smart Citation

Suspended Sediment Concentration Estimation from Landsat Imagery along the Lower Missouri and Middle Mississippi Rivers Using an Extreme Learning Machine

et al. 2018

Self Cite

View full text Add to dashboard Cite

Monitoring and quantifying suspended sediment concentration (SSC) along major fluvial systems such as the Missouri and Mississippi Rivers provide crucial information for biological processes, hydraulic infrastructure, and navigation. Traditional monitoring based on in situ measurements lack the spatial coverage necessary for detailed analysis. This study developed a method for quantifying SSC based on Landsat imagery and corresponding SSC data obtained from United States Geological Survey monitoring stations from 1982 to present. The presented methodology first uses feature fusion based on canonical correlation analysis to extract pertinent spectral information, and then trains a predictive reflectance-SSC model using a feed-forward neural network (FFNN), a cascade forward neural network (CFNN), and an extreme learning machine (ELM). The trained models are then used to predict SSC along the Missouri-Mississippi River system. Results demonstrated that the ELM-based technique generated R 2 > 0.9 for Landsat 4-5, Landsat 7, and Landsat 8 sensors and accurately predicted both relatively high and low SSC displaying little to no overfitting. The ELM model was then applied to Landsat images producing quantitative SSC maps. This study demonstrates the benefit of ELM over traditional modeling methods for the prediction of SSC based on satellite data and its potential to improve sediment transport and monitoring along large fluvial systems.

show abstract

Section: Regression Modelingmentioning

confidence: 99%

“…where x i is the input, y is the actual output, andŷ i is the predicted output. ω j ∈ R d is the weight vector, and b j is the bias of the j hidden node [43], and h(·) is a nonlinear activation function. The j output weight vector, denoted as β j , is the output weight and links the j hidden node and the output node.…”

Section: Regression Modelingmentioning

confidence: 99%

Suspended Sediment Concentration Estimation from Landsat Imagery along the Lower Missouri and Middle Mississippi Rivers Using an Extreme Learning Machine

et al. 2018

Self Cite

View full text Add to dashboard Cite

show abstract

“…The newly incorporated yellow band has been found to be correlated with AGB with a coefficient of 0.620 at p = 0.01. Maimaitijiang et al [32] have found that the yellow band has high sensitivity for low-nitrogen savanna grasses because of the high sensitivity of this band to subtle changes in the chlorophyll content. Vegetation indices are sensitive to various outside factors, such as atmospheric disturbances.…”

Section: Relationship Of the Measured Agb With Remote Sensing Variablesmentioning

confidence: 99%

Biomass Estimation for Semiarid Vegetation and Mine Rehabilitation Using Worldview-3 and Sentinel-1 SAR Imagery

Bao

et al. 2019

Remote Sensing

View full text Add to dashboard Cite

The surface mining activities in grassland and rangeland zones directly affect the livestock production, forage quality, and regional grassland resources. Mine rehabilitation is necessary for accelerating the recovery of the grassland ecosystem. In this work, we investigate the integration of data obtained via a synthetic aperture radar (Sentinel-1 SAR) with data obtained by optical remote sensing (Worldview-3, WV-3) in order to monitor the conditions of a vegetation area rehabilitated after coal mining in North China. The above-ground biomass (AGB) is used as an indicator of the rehabilitated vegetation conditions and the success of mine rehabilitation. The wavelet principal component analysis is used for the fusion of the WV-3 and Sentinel-1 SAR images. Furthermore, a multiple linear regression model is applied based on the relationship between the remote sensing features and the AGB field measurements. Our results show that WV-3 enhanced vegetation indices (EVI), mean texture from band8 (near infrared band2, NIR2), the SAR vertical and horizon (VH) polarization, and band 8 (NIR2) from the fused image have higher correlation coefficient value with the field-measured AGB. The proposed AGB estimation model combining WV-3 and Sentinel 1A SAR imagery yields higher model accuracy (R 2 = 0.79 and RMSE = 22.82 g/m 2 ) compared to that obtained with any of the two datasets only. Besides improving AGB estimation, the proposed model can also reduce the uncertainty range by 7 g m −2 on average. These results demonstrate the potential of new multispectral high-resolution datasets, such as Sentinel-1 SAR and Worldview-3, in providing timely and accurate AGB estimation for mine rehabilitation planning and management.

show abstract

“…Recent studies have demonstrated the possibility to improve the segmentation of plant-soil pixels, e.g., using Support Vector Machine (SVM) classification or Convolutional Neural Networks [27,33,34]; (ii) aerial-based sensing has an advantage over ground-based sensing platforms in generating surface maps in real time and measuring plant parameters from a large number of plots at a time, typically associated with the time required to make ground-based measurements in large trials [12,13]; (iii) using high-resolution and low-altitude UAVs can overcome further limitations of ground-based sensing platforms, such as the non-simultaneous measurement of different plots, trafficability, row, and plot geometries requiring specific sensor configurations, and vibrations resulting from uneven field surfaces [12,28]. Given that the operation of UAV image acquisition is less labor-intensive, and owing to improved segmentation procedures and a higher precision than non-imaging proximal sensing, aerial-based multispectral sensing via UAV is expected to increase the efficiency of high-throughput phenotyping in large-scale plant breeding programs [10,12].…”

Section: Heritability Of Spectral Indices In Different Row Variantsmentioning

confidence: 99%

“…These studies have also demonstrated that high-throughput phenotyping from ground-based sensing could not only contribute to savings in time and costs, but also allow for more objective information and even re-assessments in later selection cycles because the objective digital data collection can be permanently stored. More importantly, the availability of unmanned aerial vehicles (UAV) has rapidly increased in recent years [9][10][11]. The aerial platforms have an advantage over ground-based sensing platforms in generating surface maps in real time and measuring plant parameters from large numbers of plots at a time [11][12][13].…”

Section: Introductionmentioning

confidence: 99%

Advancing High-Throughput Phenotyping of Wheat in Early Selection Cycles

Knapp

Schmidhalter

2020

Remote Sensing

View full text Add to dashboard Cite

Enhancing plant breeding to ensure global food security requires new technologies. For wheat phenotyping, only limited seeds and resources are available in early selection cycles. This forces breeders to use small plots with single or multiple row plots in order to include the maximum number of genotypes/lines for their assessment. High-throughput phenotyping through remote sensing may meet the requirements for the phenotyping of thousands of genotypes grown in small plots in early selection cycles. Therefore, the aim of this study was to compare the performance of an unmanned aerial vehicle (UAV) for assessing the grain yield of wheat genotypes in different row numbers per plot in the early selection cycles with ground-based spectral sensing. A field experiment consisting of 32 wheat genotypes with four plot designs (1, 2, 3, and 12 rows per plot) was conducted. Near infrared (NIR)-based spectral indices showed significant correlations (p < 0.01) with the grain yield at flowering to grain filling, regardless of row numbers, indicating the potential of spectral indices as indirect selection traits for the wheat grain yield. Compared with terrestrial sensing, aerial-based sensing from UAV showed consistently higher levels of association with the grain yield, indicating that an increased precision may be obtained and is expected to increase the efficiency of high-throughput phenotyping in large-scale plant breeding programs. Our results suggest that high-throughput sensing from UAV may become a convenient and efficient tool for breeders to promote a more efficient selection of improved genotypes in early selection cycles. Such new information may support the calibration of genomic information by providing additional information on other complex traits, which can be ascertained by spectral sensing.

show abstract

Unmanned Aerial System (UAS)-based phenotyping of soybean using multi-sensor data fusion and extreme learning machine

Cited by 300 publications

References 125 publications

Suspended Sediment Concentration Estimation from Landsat Imagery along the Lower Missouri and Middle Mississippi Rivers Using an Extreme Learning Machine

Suspended Sediment Concentration Estimation from Landsat Imagery along the Lower Missouri and Middle Mississippi Rivers Using an Extreme Learning Machine

Biomass Estimation for Semiarid Vegetation and Mine Rehabilitation Using Worldview-3 and Sentinel-1 SAR Imagery

Advancing High-Throughput Phenotyping of Wheat in Early Selection Cycles

Contact Info

Product

Resources

About