Frost damage to maize in northeast India: assessment and estimated loss of yield by hyperspectral proximal remote sensing

Choudhury, B. U.; Webster, R.; Sharma, Vikash; Goswami, Jonali; Meetei, Thounaojam Thomas; Rangappa, Krishnappa; Raju, P. L. N.

doi:10.1117/1.jrs.13.044527

Cited by 17 publications

(11 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Remote sensing based on Unmanned Aerial Vehicle (UAV), a newly developed technique for high-throughput crop growth information acquisition, has been widely used in crop monitoring under growth ( Jiang et al., 2022 )and various stresses such as pests, diseases, water deficit, salt-stressed( Johansen et al., 2019 ) and frost( Wójtowicz et al., 2016 ; Perry et al., 2017a ; Chen et al., 2019 ; Choudhury et al., 2019 ; Goswami et al., 2019 ; Jełowicki et al., 2020 ; Millan et al., 2020 ; Marin et al., 2021 ). Although satellite remote sensing technology was also used in frost damage monitoring( Feng et al., 2009 ; Romanov, 2009 ; Romani et al., 2011 ; Rudorff et al., 2012 ; She et al., 2015 ; She et al., 2017 ; Li et al., 2021 ; Gabbrielli et al., 2022a ; Gabbrielli et al., 2022b ), the UAV-based remote sensing is more accurate in the breeding field due to its high spatial resolution.…”

Section: Introductionmentioning

confidence: 99%

“…UAVs, including DJI, 3D Robotics solo and Ebee, were equipped with spectral cameras to detect frost damage of crops such as wheat( Guo et al., 2014 ; Wang et al., 2014 ; Murphy et al., 2020 ), maize( Choudhury et al., 2019 ; Goswami et al., 2019 ; Shu et al., 2022 ), oat( Macedo-Cruz et al., 2011 ), oilseed rape( She et al., 2015 ), and coffee plants( Marin et al., 2021 ; Marin et al., 2022 ). In these studies, data analysis techniques such as Pearson correlation analysis and principal component analysis were used to extract stress-related spectral features including the reflectance of different spectral bands and several commonly used vegetation indexes (VIs) such as normalized difference vegetation index (NDVI)( She et al., 2015 ), green NDVI, photochemical reflectance index (PRI), carotenoid reflectance index(CRI), and anthocyanin reflectance index(ARI)( Choudhury et al., 2019 ; Marin et al., 2021 ; Marin et al., 2022 ). Pixel-based classification with thresholds, random forest, random committee, support vector machine (SVM) and other classification methods were used to predict frost damage degree in some of these studies( Goswami et al., 2019 ; Jełowicki et al., 2020 ).…”

Section: Introductionmentioning

confidence: 99%

“…Pixel-based classification with thresholds, random forest, random committee, support vector machine (SVM) and other classification methods were used to predict frost damage degree in some of these studies( Goswami et al., 2019 ; Jełowicki et al., 2020 ). Besides, regression methods such as multiple linear regression (MLR) and principal component regression were employed to predict crop yield or other physical parameters and then their changes before and after frost damage were compared to assess stress severity( Guo et al., 2014 ; Choudhury et al., 2019 ). Currently, several studies have utilized RGB and multispectral image features for lettuce, such as prediction of lettuce health( Pham et al., 2019 ), detection of lettuce anthocyanin content( Kim and Van Iersel, 2023 ) and classification of lettuce seeds( Concepcion et al., 2020 ).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Estimating the frost damage index in lettuce using UAV-based RGB and multispectral images

Liu,

Ban,

Wei

et al. 2024

Front. Plant Sci.

View full text Add to dashboard Cite

IntroductionThe cold stress is one of the most important factors for affecting production throughout year, so effectively evaluating frost damage is great significant to the determination of the frost tolerance in lettuce.MethodsWe proposed a high-throughput method to estimate lettuce FDI based on remote sensing. Red-Green-Blue (RGB) and multispectral images of open-field lettuce suffered from frost damage were captured by Unmanned Aerial Vehicle platform. Pearson correlation analysis was employed to select FDI-sensitive features from RGB and multispectral images. Then the models were established for different FDI-sensitive features based on sensor types and different groups according to lettuce colors using multiple linear regression, support vector machine and neural network algorithms, respectively.Results and discussionDigital number of blue and red channels, spectral reflectance at blue, red and near-infrared bands as well as six vegetation indexes (VIs) were found to be significantly related to the FDI of all lettuce groups. The high sensitivity of four modified VIs to frost damage of all lettuce groups was confirmed. The average accuracy of models were improved by 3% to 14% through a combination of multisource features. Color of lettuce had a certain impact on the monitoring of frost damage by FDI prediction models, because the accuracy of models based on green lettuce group were generally higher. The MULTISURCE-GREEN-NN model with R2 of 0.715 and RMSE of 0.014 had the best performance, providing a high-throughput and efficient technical tool for frost damage investigation which will assist the identification of cold-resistant green lettuce germplasm and related breeding.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Estimating the frost damage index in lettuce using UAV-based RGB and multispectral images

Liu,

Ban,

Wei

et al. 2024

Front. Plant Sci.

View full text Add to dashboard Cite

show abstract

“…Spring frost occurs when the temperature drops below 0 °C after warming up in spring, thus seriously endangering the yield of agricultural and forestry plants, such as maize, wheat, apple and apricot [4][5][6][7]. Moreover, with the trend of global warming, the temperature increases in early spring, which makes plants more susceptible to spring frost.…”

Section: Introductionmentioning

confidence: 99%

Identification of key gene networks related to the freezing resistance of apricot kernel pistils by integrating hormone phenotypes and transcriptome profiles

Liu

et al. 2022

BMC Plant Biol

View full text Add to dashboard Cite

Background Apricot kernel, a woody oil tree species, is known for the high oil content of its almond that can be used as an ideal feedstock for biodiesel production. However, apricot kernel is vulnerable to spring frost, resulting in reduced or even no yield. There are no effective countermeasures in production, and the molecular mechanisms underlying freezing resistance are not well understood. Results We used transcriptome and hormone profiles to investigate differentially responsive hormones and their associated co-expression patterns of gene networks in the pistils of two apricot kernel cultivars with different cold resistances under freezing stress. The levels of auxin (IAA and ICA), cytokinin (IP and tZ), salicylic acid (SA) and jasmonic acid (JA and ILE-JA) were regulated differently, especially IAA between two cultivars, and external application of an IAA inhibitor and SA increased the spring frost resistance of the pistils of apricot kernels. We identified one gene network containing 65 hub genes highly correlated with IAA. Among these genes, three genes in auxin signaling pathway and three genes in brassinosteroid biosynthesis were identified. Moreover, some hub genes in this network showed a strong correlation such as protein kinases (PKs)-hormone related genes (HRGs), HRGs-HRGs and PKs-Ca2+ related genes. Conclusions Ca2+, brassinosteroid and some regulators (such as PKs) may be involved in an auxin-mediated freezing response of apricot kernels. These findings add to our knowledge of the freezing response of apricot kernels and may provide new ideas for frost prevention measures and high cold–resistant apricot breeding.

show abstract

“…It can provide abundant and accurate spectral information of crops. Recently, many researchers proposed to use multispectral or hyperspectral images collected by UAVs to recognize the crop freezing injury [14][15][16]. In general, they firstly calculated different vegetation indices (VIs) using source images, and then several VIs are combined to recognize the freezing-injured crops.…”

Section: Introductionmentioning

confidence: 99%

Automatic Freezing-Tolerant Rapeseed Material Recognition Using UAV Images and Deep Learning

Qiao

Yao

et al. 2021

Preprint

View full text Add to dashboard Cite

Background: Freezing injury is a serious and common damage that occurs to winter rapeseed during the overwintering period. The freezing injury directly reduces the rapeseed yield and causes serious economic loss. Thus, it is an important and urgent task for crop breeders to find the freezing-tolerant rapeseed materials in the process of breeding. Existing large-scale freezing-tolerant rapeseed material recognition methods mainly rely on the field investigation conducted by the agricultural experts using some professional equipment. These methods are time-consuming, inefficient and laborious. In addition, the accuracy of these traditional methods depends heavily on the knowledge and experience of experts. Methods: To solve these problems of existing methods, we propose a low-cost freezing-tolerant rapeseed material recognition approach using deep learning technology and unmanned aerial vehicle (UAV) images captured by a consumer drone. We formulate the problem of freezing-tolerant material recognition as a binary classification problem, which can be solved well using deep learning technology. The proposed method can automatically and efficiently recognize the freezing-tolerant rapeseed materials from a large number of candidates. To train the deep learning network, we first manually construct the real dataset using the UAV images of rapeseed materials collected by the Phantom 4 Pro. Then, five classic deep learning networks (AlexNet, VGGNet16, ResNet18, ResNet50 and GoogLeNet) are selected to perform the freezing-tolerant rapeseed material recognition. Result and Conclusion: The accuracy of the five deep learning networks used in our work is all over 92%. Especially, ResNet50 provides the best accuracy (93.33%) in this task. In addition, we also compare deep learning networks with traditional machine learning methods. The comparison results show that the deep learning-based approach significantly outperforms the traditional machine learning-based methods in our task. The experimental results show that it is feasible to recognize the freezing-tolerant rapeseed using UAV images and deep learning.

show abstract

Frost damage to maize in northeast India: assessment and estimated loss of yield by hyperspectral proximal remote sensing

Cited by 17 publications

References 19 publications

Estimating the frost damage index in lettuce using UAV-based RGB and multispectral images

Estimating the frost damage index in lettuce using UAV-based RGB and multispectral images

Identification of key gene networks related to the freezing resistance of apricot kernel pistils by integrating hormone phenotypes and transcriptome profiles

Automatic Freezing-Tolerant Rapeseed Material Recognition Using UAV Images and Deep Learning

Contact Info

Product

Resources

About