scholarly journals Applying Machine Learning to Investigate Long Term Insect-Plant Interactions Preserved on Digitized Herbarium Specimens

2019 ◽  
Author(s):  
E.K. Meineke ◽  
C. Tomasi ◽  
S. Yuan ◽  
K.M. Pryer
Keyword(s):  
Machine Learning ◽  
Herbarium Specimens ◽  
Insect Damage ◽  
Similar Data ◽  
Plant Interactions ◽  
Plant Insect Interactions ◽  
Related Plant ◽  
Insect Interactions ◽  
Damage Type

AbstractPremise of the studyDespite the economic importance of insect damage to plants, long-term data documenting changes in insect damage (‘herbivory’) and diversity are limited. Millions of pressed plant specimens are now available online for collecting big data on plant-insect interactions during the Anthropocene.MethodsWe initiated development of machine learning methods to automate extraction of herbivory data from herbarium specimens. We trained an insect damage detector and a damage type classifier on two distantly related plant species. We experimented with 1) classifying six types of herbivory and two control categories of undamaged leaf, and 2) detecting two of these damage categories for which several hundred annotations were available.ResultsClassification models identified the correct type of herbivory 81.5% of the time. The damage classifier was accurate for categories with at least one hundred test samples. We show anecdotally that the detector works well when asked to detect two types of damage.DiscussionThe classifier and detector together are a promising first step for the automation of herbivory data collection. We describe ongoing efforts to increase the accuracy of these models to allow other researchers to extract similar data and apply them to address a variety of biological hypotheses.

scholarly journals Herbarium specimens reveal herbivory patterns across the genus Cucurbita

2021 ◽  
Author(s):  
Laura A. Jenny ◽  
Lori R. Shapiro ◽  
Charles C. Davis ◽  
T. Jonathan Davies ◽  
Naomi E. Pierce ◽  
...  
Keyword(s):  
Insect Herbivory ◽  
Herbarium Specimens ◽  
Ecological Interactions ◽  
Native Range ◽  
Geographic Ranges ◽  
Plant Insect Interactions ◽  
New Methods ◽  
Related Plant ◽  
Insect Interactions

PREMISE: Quantifying how closely related plant species differ in susceptibility to insect herbivory is important for our understanding of variation in plant-insect ecological interactions and evolutionary pressures on plant functional traits. However, empirically measuring in situ variation in herbivory over the entire geographic range where a plant-insect complex occurs is logistically difficult. Recently, new methods have been developed to use herbarium specimens to investigate patterns in plant-insect interactions across geographic areas, and during periods of accelerating anthropogenic change. Such investigations can provide insights into changes in herbivory intensity and phenology in plants that are of ecological and agricultural importance. METHODS: Here, we analyze 274 pressed herbarium samples from all 14 species in the economically important plant genus Cucurbita (Cucurbitaceae) to investigate variation in herbivory damage. This collection is comprised of specimens of wild, undomesticated Cucurbita that were collected from across their native range in the Neotropics and subtropics, and Cucurbita cultivars that were collected from both within their native range and from locations where they have been introduced for agriculture in temperate Eastern North America. RESULTS: We find that herbivory is common on individuals of all Cucurbita species collected from throughout their geographic ranges; however, estimates of herbivory varied considerably among individuals, with greater damage observed in specimens collected from unmanaged habitat. We also find evidence that mesophytic species accrue more insect damage than xerophytic species. CONCLUSIONS: Our study demonstrates that herbarium specimens are a useful resource for understanding ecological interactions between domesticated crop plants and co-evolved insect herbivores.

Averting robo-bees: why free-flying robotic bees are a bad idea

2019 ◽  
Vol 3 (6) ◽  
pp. 723-729
Author(s):  
Roslyn Gleadow ◽  
Jim Hanan ◽  
Alan Dorin
Keyword(s):  
Climate Change ◽  
Computer Simulation ◽  
Food Security ◽  
European Countries ◽  
Plant Interactions ◽  
Plant Insect Interactions ◽  
Native Habitat ◽  
Insect Pollinators ◽  
Insect Interactions

Food security and the sustainability of native ecosystems depends on plant-insect interactions in countless ways. Recently reported rapid and immense declines in insect numbers due to climate change, the use of pesticides and herbicides, the introduction of agricultural monocultures, and the destruction of insect native habitat, are all potential contributors to this grave situation. Some researchers are working towards a future where natural insect pollinators might be replaced with free-flying robotic bees, an ecologically problematic proposal. We argue instead that creating environments that are friendly to bees and exploring the use of other species for pollination and bio-control, particularly in non-European countries, are more ecologically sound approaches. The computer simulation of insect-plant interactions is a far more measured application of technology that may assist in managing, or averting, ‘Insect Armageddon' from both practical and ethical viewpoints.

FIRST EVIDENCE OF SEED PREDATION BY ARTHROPODS FROM GONDWANA AND ITS EARLY PALEOZOIC HISTORY (RIO BONITO FORMATION, PARANÁ BASIN, BRAZIL)

Palaios ◽  
2020 ◽  
Vol 35 (7) ◽  
pp. 292-301
Author(s):  
THAMIRIS BARBOSA DOS SANTOS ◽  
ESTHER REGINA DE SOUZA PINHEIRO ◽  
ROBERTO IANNUZZI
Keyword(s):  
Seed Predation ◽  
Scale Insect ◽  
Lower Permian ◽  
Plant Organs ◽  
Plant Insect Interactions ◽  
Elevated Frequency ◽  
Insect Interactions ◽  
Damage Type ◽  
Damage Types ◽  
Plant Insect Interaction

ABSTRACT Seeds are plant organs commonly found worldwide in late Paleozoic deposits. In Gondwana, the seeds are found in deposits from Southern Africa, Antarctica, Oceania, and South America, and are widely reported in the well-known “Glossopteris Flora”. Even with a significant record of these plant organs, little is known about plant-insect interactions with seeds during the Pennsylvanian and Permian periods. In the present paper, we recorded the first formal record of seed consumption by arthropods in Cordaicarpus and Samaropsis-like seeds for Gondwana from lower Permian (Artinskian) deposits in Southern Brazil. The material analyzed was collected from the Itanema II outcrop of Santa Catarina State and consisted of 34 seed specimens. Of these, eight specimens presented evidence for plant-insect interaction, representing 23.5% of all specimens that were attacked by seed predators. The consumption was inflicted by insects with stylate mouthparts, probably belonging to hemipteroid or paleodictyopteroid lineages. The damage is described as perforations and scale-insect marks along the seed body. We recorded one damage type as DT74 and three others as new damage types DT399, DT400, and DT401, some of which are specific to a few seed morphotypes, including one morphotype with subtending cupule still attached to the seed. The elevated frequency of seed predation indicates that seed consumption by insects was well established during the early Permian.

scholarly journals Direct and legacy effects of long-term elevated CO2on fine root growth and plant-insect interactions

2013 ◽  
Vol 200 (3) ◽  
pp. 788-795 ◽  
Author(s):  
Peter Stiling ◽  
Daniel Moon ◽  
Anthony Rossi ◽  
Rebecca Forkner ◽  
Bruce A. Hungate ◽  
...  
Keyword(s):  
Root Growth ◽  
Fine Root ◽  
Legacy Effects ◽  
Plant Insect Interactions ◽  
Fine Root Growth ◽  
Insect Interactions

scholarly journals The Multifunctional Roles of Polyphenols in Plant-Herbivore Interactions

2021 ◽  
Vol 22 (3) ◽  
pp. 1442
Author(s):  
Sukhman Singh ◽  
Ishveen Kaur ◽  
Rupesh Kariyat
Keyword(s):  
Secondary Metabolites ◽  
Biologically Active ◽  
Future Research ◽  
Plant Interactions ◽  
Plant Insect Interactions ◽  
Physical Defenses ◽  
Herbivore Interactions ◽  
Insect Interactions ◽  
Plant Herbivore

There is no argument to the fact that insect herbivores cause significant losses to plant productivity in both natural and agricultural ecosystems. To counter this continuous onslaught, plants have evolved a suite of direct and indirect, constitutive and induced, chemical and physical defenses, and secondary metabolites are a key group that facilitates these defenses. Polyphenols—widely distributed in flowering plants—are the major group of such biologically active secondary metabolites. Recent advances in analytical chemistry and metabolomics have provided an opportunity to dig deep into extraction and quantification of plant-based natural products with insecticidal/insect deterrent activity, a potential sustainable pest management strategy. However, we currently lack an updated review of their multifunctional roles in insect-plant interactions, especially focusing on their insect deterrent or antifeedant properties. This review focuses on the role of polyphenols in plant-insect interactions and plant defenses including their structure, induction, regulation, and their anti-feeding and toxicity effects. Details on mechanisms underlying these interactions and localization of these compounds are discussed in the context of insect-plant interactions, current findings, and potential avenues for future research in this area.

scholarly journals A case of long-term herbivory: specialized feeding trace on Parrotia (Hamamelidaceae) plant species

2020 ◽  
Vol 7 (10) ◽  
pp. 201449
Author(s):  
Benjamin Adroit ◽  
Xin Zhuang ◽  
Torsten Wappler ◽  
Jean-Frederic Terral ◽  
Bo Wang
Keyword(s):  
Western Europe ◽  
Environmental Changes ◽  
Terrestrial Ecosystems ◽  
Insect Damage ◽  
Ecosystem Structure ◽  
Biogeographic History ◽  
Fossil Leaves ◽  
Continuous Presence ◽  
Insect Interactions

Interactions between plants and insects evolved during millions of years of coevolution and maintain the trophic balance of terrestrial ecosystems. Documenting insect damage types (DT) on fossil leaves is essential for understanding the evolution of plant–insect interactions and for understanding the effects of major environmental changes on ecosystem structure. However, research focusing on palaeoherbivory is still sparse and only a tiny fraction of fossil leaf collections have been analysed. This study documents a type of insect damage found exclusively on the leaves of Parrotia species (Hamamelidaceae). This DT was identified on Parrotia leaves from Willershausen (Germany, Pliocene) and from Shanwang (China, Miocene) and on their respective endemic modern relatives: Parrotia perisca in the Hyrcanian forests (Iran) and Parrotia subaequalis in the Yixing forest (China). Our study demonstrates that this insect DT persisted over at least 15 Myr spanning eastern Asia to western Europe. Against expectations, more examples of this type of herbivory were identified on the fossil leaves than on the modern examples. This mismatch may suggest a decline of this specialized plant–insect interaction owing to the contraction of Parrotia populations in Eurasia during the late Cenozoic. However, the continuous presence of this DT demonstrates a robust and long-term plant–herbivore association, and provides new evidence for a shared biogeographic history of the two host plants.

scholarly journals Global soil moisture data derived through machine learning trained with in-situ measurements

2021 ◽  
Vol 8 (1) ◽  
Author(s):  
Sungmin O. ◽  
Rene Orth
Keyword(s):  
Machine Learning ◽  
Soil Moisture ◽  
Large Scale ◽  
Short Term Memory ◽  
Temporal Dynamics ◽  
Soil Moisture Data ◽  
Wide Range ◽  
Global Soil

AbstractWhile soil moisture information is essential for a wide range of hydrologic and climate applications, spatially-continuous soil moisture data is only available from satellite observations or model simulations. Here we present a global, long-term dataset of soil moisture derived through machine learning trained with in-situ measurements, SoMo.ml. We train a Long Short-Term Memory (LSTM) model to extrapolate daily soil moisture dynamics in space and in time, based on in-situ data collected from more than 1,000 stations across the globe. SoMo.ml provides multi-layer soil moisture data (0–10 cm, 10–30 cm, and 30–50 cm) at 0.25° spatial and daily temporal resolution over the period 2000–2019. The performance of the resulting dataset is evaluated through cross validation and inter-comparison with existing soil moisture datasets. SoMo.ml performs especially well in terms of temporal dynamics, making it particularly useful for applications requiring time-varying soil moisture, such as anomaly detection and memory analyses. SoMo.ml complements the existing suite of modelled and satellite-based datasets given its distinct derivation, to support large-scale hydrological, meteorological, and ecological analyses.

Sign in / Sign up

Export Citation Format

Share Document