Scientific review of the impact of climate change on plant pests

Gullino, M. L.; Albales, R.; Al-Jboory, Ibrahim; Angelotti, Francislene; Chakraborty, Subrata; Garrett, Karen A.; Hurley, B. P.; Juroszek, Peter; Makkouk, K. M.; Stephenson, Tannecia S.

doi:10.4060/cb4769en

Cited by 56 publications

(16 citation statements)

References 179 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, false positives occurred in only 3 of the 88 images. Multiple errors can be seen in Figure 4: (1) grapes in the background, (2) confusion with the ground and (3) the segmented crates are not completely separated. These kind of errors can be easily removed with morphological operations.…”

Section: Segmentation Modelmentioning

confidence: 99%

See 1 more Smart Citation

Lite CNN Models for Real-Time Post-Harvest Grape Disease Detection

Mohimont

Alin

Gaveau

et al. 2022

Ambient Intelligence and Smart Environments

View full text Add to dashboard Cite

Post-harvest fruit grading is a necessary step to avoid disease related loss in quality. In this paper, a hierarchical method is proposed to (1) remove the background and (2) detect images that contains grape diseases(botrytis, oidium, acid rot). Satisfying segmentation performances were obtained by the proposed Lite Unet model with 92.9% IoU score and an average speed of 0.16s/image. A pretrained MobileNet-V2 model obtained 94% F1 score on disease classification. An optimized CNN reached a score of 89% with less than 10 times less parameters. The implementation of both segmentation and classification models on low-powered device would allow for real-time disease detection at the press.

show abstract

Section: Segmentation Modelmentioning

confidence: 99%

“…Diseases are directly responsible for yield and quality loss in many cultivars. The Food and Agriculture Organization of the United Nation estimates that plant diseases and invasive insects are responsible for 20% to 40% worldwide yield loss [1]. Disease detection is therefore an important problem in the field of Smart Agriculture.…”

Section: Introductionmentioning

confidence: 99%

Lite CNN Models for Real-Time Post-Harvest Grape Disease Detection

Mohimont

Alin

Gaveau

et al. 2022

Ambient Intelligence and Smart Environments

View full text Add to dashboard Cite

show abstract

“…The copyright holder for this preprint (which this version posted April 29, 2023. ; https://doi.org/10.1101/2023.04.27.538617 doi: bioRxiv preprint (Greenwood et al 2017;Onyekachi et al 2019), pest susceptibility (Jaime et al 2019;IPPC Secretariat 2021), and phenological mismatches (Beard et al 2019). Two plant-related factors that can predict crop yield decline in relation to dwindling pollination services and climate change are pollinator dependence and growth form, respectively.…”

Section: Introductionmentioning

confidence: 99%

Being a tree crop increases the odds of experiencing yield declines irrespective of pollinator dependence

Aizen

Gleiser

Kitzberger

et al. 2023

Preprint

View full text Add to dashboard Cite

Yields are in decline for a number of crops and regions, but the drivers of this process are poorly known. Global decreases in pollinator abundance and diversity have been proposed as a major driver of yield declines in crops that depend on animals, mostly bees, to produce fruits and seeds. Alternatively, widespread tree mortality has been directly and indirectly related to global climate change, which could also explain yield decreases in tree crops. As tree crops are expected to be more dependent on pollinators than other crop types, disentangling the relative influence of growth form and pollinator dependence is relevant to identify the ultimate factors driving yield declines. The incidence of yield decline, estimated as a negative average yield growth rate from 1961 to 2020, was measured in 4270 time series, involving 136 crops and 163 countries and territories. About one-fourth of all time series showed negative average rates of yield growth, a characteristic associated with both high pollinator dependence and a tree growth form. Because pollinator dependence and plant growth form were partially correlated, we disentangled the effect of each of these two predictors using a series of generalized linear mixed models that evaluated direct and indirect associations. Our analyses revealed a stronger association of yield decline with growth form than with pollinator dependence, a relationship that persisted after partialling out the effect of pollinator dependence. In particular, yield declines were more common among tree than herbaceous and shrub crops in all major regions but in Africa, a continent showing a high incidence of yield declines irrespective of growth form. These results suggest that global climate change rather than pollinator decline could already be impacting tree crop productivity.

show abstract

“…Insect pests cause yield losses of up to 40% globally, with estimated revenue losses of $220 billion (Gullino et al, 2021). Insect populations are influenced by temperature and other environmental conditions, so future climate change is predicted to affect insect-pest outbreaks (Liebhold & Bentz, 2011;Skendžić et al, 2021).…”

Section: Introductionmentioning

confidence: 99%

Self‐supervised learning improves classification of agriculturally important insect pests in plants

Kar

Nagasubramanian

Elango

et al. 2023

The Plant Phenome Journal

View full text Add to dashboard Cite

Insect pests cause significant damage to food production, so early detection and efficient mitigation strategies are crucial. There is a continual shift toward machine learning (ML)‐based approaches for automating agricultural pest detection. Although supervised learning has achieved remarkable progress in this regard, it is impeded by the need for significant expert involvement in labeling the data used for model training. This makes real‐world applications tedious and oftentimes infeasible. Recently, self‐supervised learning (SSL) approaches have provided a viable alternative to training ML models with minimal annotations. Here, we present an SSL approach to classify 22 insect pests. The framework was assessed on raw and segmented field‐captured images using three different SSL methods, Nearest Neighbor Contrastive Learning of Visual Representations (NNCLR), Bootstrap Your Own Latent, and Barlow Twins. SSL pre‐training was done on ResNet‐18 and ResNet‐50 models using all three SSL methods on the original RGB images and foreground segmented images. The performance of SSL pre‐training methods was evaluated using linear probing of SSL representations and end‐to‐end fine‐tuning approaches. The SSL‐pre‐trained convolutional neural network models were able to perform annotation‐efficient classification. NNCLR was the best performing SSL method for both linear and full model fine‐tuning. With just 5% annotated images, transfer learning with ImageNet initialization obtained 74% accuracy, whereas NNCLR achieved an improved classification accuracy of 79% for end‐to‐end fine‐tuning. Models created using SSL pre‐training consistently performed better, especially under very low annotation, and were robust to object class imbalances. These approaches help overcome annotation bottlenecks and are resource efficient.

show abstract

Scientific review of the impact of climate change on plant pests

Abstract: Scientific review of the impact of climate change on plant pests -A global challenge to prevent and mitigate plant pest risks in agriculture, forestry and ecosystems. Rome. FAO on behalf of the IPPC Secretariat.

Cited by 56 publications

References 179 publications

Lite CNN Models for Real-Time Post-Harvest Grape Disease Detection

Lite CNN Models for Real-Time Post-Harvest Grape Disease Detection

Being a tree crop increases the odds of experiencing yield declines irrespective of pollinator dependence

Self‐supervised learning improves classification of agriculturally important insect pests in plants

Contact Info

Product

Resources

About