scholarly journals Using Deep Learning to Count Monarch Butterflies in Dense Clusters

2021 ◽  
Author(s):  
Shruti Patel ◽  
Amogh Kulkarni ◽  
Ayan Mukhopadhyay ◽  
Karuna Gujar ◽  
Jaap de Roode
Keyword(s):  
Climate Change ◽  
Open Source ◽  
Population Size ◽  
High Accuracy ◽  
Central Mexico ◽  
Deep Convolutional Neural Networks ◽  
Monarch Butterflies ◽  
Migration Patterns ◽  
Breeding Grounds ◽  
High Resolution Images

Monarch butterflies display one of the most fascinating migration patterns of all species, traveling over 3000 miles from their North American breeding grounds to reach overwintering sites in Central Mexico. Recent studies have suggested that monarchs have experienced an alarming decline in population size due to a combination of deforestation, loss of native milkweed and nectaring plants, and climate change. An issue that conservation efforts face is the lack of principled mechanisms to accurately estimate and count the population size of monarchs. This difficulty occurs due to their small size and existence in dense overwintering clusters in forests. We create an open-source tool to aid conservationists estimate the count of monarch butterflies from images automatically. To the best of our knowledge, our approach, based on deep convolutional neural networks, is the first automated application that can count small insects like monarch butterflies in dense clusters. We demonstrate that our approach achieves high accuracy in counting the number of butterflies even in the presence of occlusion. We also release an open-source dataset containing high resolution images of monarch butterflies along with human annotations for each butterfly's position. Our open-source implementation can be readily used by scientists to estimate monarch numbers in overwintering clusters.

scholarly journals NetCleave: an open-source algorithm for predicting C-terminal antigen processing for MHC-I and MHC-II

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Pep Amengual-Rigo ◽  
Victor Guallar
Keyword(s):  
Open Source ◽  
Antigen Processing ◽  
High Accuracy ◽  
Biological Processes ◽  
Mhc I ◽  
Mhc Ii ◽  
Prediction Tools ◽  
Immunogenic Peptides ◽  
Physicochemical Descriptors ◽  
Peptide Presentation

AbstractAntigens presented on the cell surface have been subjected to multiple biological processes. Among them, C-terminal antigen processing constitutes one of the main bottlenecks of the peptide presentation pathways, as it delimits the peptidome that will be subjected downstream. Here, we present NetCleave, an open-source and retrainable algorithm for the prediction of the C-terminal antigen processing for both MHC-I and MHC-II pathways. NetCleave architecture consists of a neural network trained on 46 different physicochemical descriptors of the cleavage site amino acids. Our results demonstrate that prediction of C-terminal antigen processing achieves high accuracy on MHC-I (AUC of 0.91), while it remains challenging for MHC-II (AUC of 0.66). Moreover, we evaluated the performance of NetCleave and other prediction tools for the evaluation of four independent immunogenicity datasets (H2-Db, H2-Kb, HLA-A*02:01 and HLA-B:07:02). Overall, we demonstrate that NetCleave stands out as one of the best algorithms for the prediction of C-terminal processing, and we provide one of the first evidence that C-terminal processing predictions may help in the discovery of immunogenic peptides.

scholarly journals Tracking multi-generational colonization of the breeding grounds by monarch butterflies in eastern North America

2013 ◽  
Vol 280 (1768) ◽  
pp. 20131087 ◽  
Author(s):  
D. T. Tyler Flockhart ◽  
Leonard I. Wassenaar ◽  
Tara G. Martin ◽  
Keith A. Hobson ◽  
Michael B. Wunder ◽  
...  
Keyword(s):  
North America ◽  
Danaus Plexippus ◽  
Late Summer ◽  
Breeding Habitat ◽  
Eastern North America ◽  
Distribution Models ◽  
Monarch Butterflies ◽  
Breeding Distribution ◽  
Breeding Grounds ◽  
Isotope Measurements

Insect migration may involve movements over multiple breeding generations at continental scales, resulting in formidable challenges to their conservation and management. Using distribution models generated from citizen scientist occurrence data and stable-carbon and -hydrogen isotope measurements, we tracked multi-generational colonization of the breeding grounds of monarch butterflies ( Danaus plexippus ) in eastern North America. We found that monarch breeding occurrence was best modelled with geographical and climatic variables resulting in an annual breeding distribution of greater than 12 million km 2 that encompassed 99% occurrence probability. Combining occurrence models with stable isotope measurements to estimate natal origin, we show that butterflies which overwintered in Mexico came from a wide breeding distribution, including southern portions of the range. There was a clear northward progression of monarchs over successive generations from May until August when reproductive butterflies began to change direction and moved south. Fifth-generation individuals breeding in Texas in the late summer/autumn tended to originate from northern breeding areas rather than regions further south. Although the Midwest was the most productive area during the breeding season, monarchs that re-colonized the Midwest were produced largely in Texas, suggesting that conserving breeding habitat in the Midwest alone is insufficient to ensure long-term persistence of the monarch butterfly population in eastern North America.

scholarly journals Macroeconomic Impacts of Climate Change Driven by Changes in Crop Yields

2018 ◽  
Vol 10 (10) ◽  
pp. 3673 ◽  
Author(s):  
Shinichiro Fujimori ◽  
Toshichika Iizumi ◽  
Tomoko Hasegawa ◽  
Jun’ya Takakura ◽  
Kiyoshi Takahashi ◽  
...  
Keyword(s):  
Climate Change ◽  
Land Use ◽  
Population Size ◽  
Large Population ◽  
Food Prices ◽  
Production Volume ◽  
Total Uncertainty ◽  
Indicator Value ◽  
Macroeconomic Impacts ◽  
Macroeconomic Indicator

Changes in agricultural yields due to climate change will affect land use, agricultural production volume, and food prices as well as macroeconomic indicators, such as GDP, which is important as it enables one to compare climate change impacts across multiple sectors. This study considered five key uncertainty factors and estimated macroeconomic impacts due to crop yield changes using a novel integrated assessment framework. The five factors are (1) land-use change (or yield aggregation method based on spatially explicit information), (2) the amplitude of the CO2 fertilization effect, (3) the use of different climate models, (4) socioeconomic assumptions and (5) the level of mitigation stringency. We found that their global impacts on the macroeconomic indicator value were 0.02–0.06% of GDP in 2100. However, the impacts on the agricultural sector varied greatly by socioeconomic assumption. The relative contributions of these factors to the total uncertainty in the projected macroeconomic indicator value were greater in a pessimistic world scenario characterized by a large population size, low income, and low yield development than in an optimistic scenario characterized by a small population size, high income, and high yield development (0.00%).

scholarly journals High accuracy detection for T-cells and B-cells using deep convolutional neural networks

2018 ◽  
Vol 5 (1) ◽  
Author(s):  
Bilal Turan ◽  
Taisuke Masuda ◽  
Anas Mohd Noor ◽  
Koji Horio ◽  
Toshiki I. Saito ◽  
...  
Keyword(s):  
Neural Networks ◽  
T Cells ◽  
B Cells ◽  
Convolutional Neural Networks ◽  
High Accuracy ◽  
Deep Convolutional Neural Networks

Effective Filter Pruning Method Using Additional Downsampled Image for Global Pooling Applied CNN

2021 ◽  
pp. 2154029
Author(s):  
Hyunseok Kim ◽  
Bunyodbek Ibrokhimov ◽  
Sanggil Kang
Keyword(s):  
Evaluation Method ◽  
Computational Cost ◽  
Information Loss ◽  
Deep Convolutional Neural Networks ◽  
Embedded Devices ◽  
Computational Costs ◽  
Pruning Method ◽  
Original Dataset ◽  
High Resolution Images ◽  
Deep Cnn

Deep Convolutional Neural Networks (CNNs) show remarkable performance in many areas. However, most of the applications require huge computational costs and massive memory, which are hard to obtain in devices with a relatively weak performance like embedded devices. To reduce the computational cost, and meantime, to preserve the performance of the trained deep CNN, we propose a new filter pruning method using an additional dataset derived by downsampling the original dataset. Our method takes advantage of the fact that information in high-resolution images is lost in the downsampling process. Each trained convolutional filter reacts differently to this information loss. Based on this, the importance of the filter is evaluated by comparing the gradient obtained from two different resolution images. We validate the superiority of our filter evaluation method using a VGG-16 model trained on CIFAR-10 and CUB-200-2011 datasets. The pruned network with our method shows an average of 2.66% higher accuracy in the latter dataset, compared to existing pruning methods when about 75% of the parameters are removed.

Changes in migration, carry-over effects, and migratory connectivity

2019 ◽  
pp. 93-107 ◽  
Author(s):  
Roberto Ambrosini ◽  
Andrea Romano ◽  
Nicola Saino
Keyword(s):  
Climate Change ◽  
Life Cycle ◽  
Population Size ◽  
Migratory Connectivity ◽  
Negative Effects ◽  
Annual Life Cycle ◽  
Northern Latitudes ◽  
Timing Of Migration ◽  
Tropical Areas ◽  
Carry Over

Studies of the timing (phenology) of bird migration provided some of the first evidence for the effects of climate change on organisms. Since the rate of climate change is uneven across the globe, with northern latitudes experiencing faster warming trends than tropical areas, animals moving across latitudes are subject to diverging trends of climate change at different stages of their annual life cycle, and, consequently, they can become mistimed with the local ecological conditions, with potentially negative effects on population size. This chapter reviews the modifications induced by climate change in different migration traits, like the timing of migration events, the distribution of organisms, and the direction and the speed of movements. It also considers the effects of ecological carry-over effects and migratory connectivity on the response of birds to climate change.

scholarly journals Arctic avian predators synchronise their spring migration with the northern progression of snowmelt

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
Teja Curk ◽  
Ivan Pokrovsky ◽  
Nicolas Lecomte ◽  
Tomas Aarvak ◽  
David F. Brinker ◽  
...  
Keyword(s):  
Large Scale ◽  
Temporal Dynamics ◽  
The Arctic ◽  
Migratory Species ◽  
Migration Patterns ◽  
Predator Species ◽  
Movement Data ◽  
Breeding Grounds ◽  
Spatio Temporal ◽  
Spring Snowmelt

Abstract Migratory species display a range of migration patterns between irruptive (facultative) to regular (obligate), as a response to different predictability of resources. In the Arctic, snow directly influences resource availability. The causes and consequences of different migration patterns of migratory species as a response to the snow conditions remains however unexplored. Birds migrating to the Arctic are expected to follow the spring snowmelt to optimise their arrival time and select for snow-free areas to maximise prey encounter en-route. Based on large-scale movement data, we compared the migration patterns of three top predator species of the tundra in relation to the spatio-temporal dynamics of snow cover. The snowy owl, an irruptive migrant, the rough-legged buzzard, with an intermediary migration pattern, and the peregrine falcon as a regular migrant, all followed, as expected, the spring snowmelt during their migrations. However, the owl stayed ahead, the buzzard stayed on, and the falcon stayed behind the spatio-temporal peak in snowmelt. Although none of the species avoided snow-covered areas, they presumably used snow presence as a cue to time their arrival at their breeding grounds. We show the importance of environmental cues for species with different migration patterns.

scholarly journals Mercury and Stable Isotopes in Feathers Of Audouin's Gulls as Indicators of Feeding Habits and Migratory Connectivity

The Condor ◽  
2007 ◽  
Vol 109 (2) ◽  
pp. 268-275 ◽  
Author(s):  
Carola Sanpera ◽  
Xavier Ruiz ◽  
Rocío Moreno ◽  
Lluís Jover ◽  
Susan Waldron
Keyword(s):  
Trophic Ecology ◽  
Feeding Habits ◽  
Geographical Area ◽  
Future Research ◽  
Migratory Connectivity ◽  
Migration Patterns ◽  
Isotopic Signatures ◽  
Breeding Populations ◽  
Breeding Grounds ◽  
Wintering Areas

Abstract To better understand migratory connectivity between breeding and nonbreeding populations, we analyzed mercury (Hg) and stable isotope signatures of nitrogen (δ15N), carbon (δ13C), and sulfur (δ34S) in Audouin's Gulls (Larus audouinii) breeding in two different colonies, the Ebro Delta (northeastern Spain) and the Chafarinas Islands (southwestern Mediterranean). Although abundant information is available on the biology and trophic ecology of this gull's breeding populations, little is known about migration patterns, distribution in winter, or conditions faced during the nonbreeding period. Analyses were carried out on first primary feathers, grown during the summer while gulls are on the breeding grounds, and mantle feathers, grown during the winter. Different isotopic signatures (δ15N, δ13C, and δ34S) in summer (primary) feathers from each area agree with the observed differences in diet between the two colonies. In winter (mantle) feathers, isotopic signatures did not differ, consistent with a common wintering ground and common diet, although the lack of isotopic basemaps in marine systems precludes assignment to a geographical area of reference. Future research is needed to relate isotopic signatures and Hg values in mantle feathers to trophic ecology in wintering areas. Results for Hg indicate that the excretory role played by primary feathers precludes their use as indicators of trophic ecology.

Sign in / Sign up

Export Citation Format

Share Document