Harnessing Deep Learning in Ecology: An Example Predicting Bark Beetle Outbreaks.
Ontology highlight
ABSTRACT:
SUBMITTER: Rammer W
PROVIDER: S-EPMC6827389 | biostudies-literature | 2019
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Bark beetle outbreaks have intensified in many forests around the globe in recent years. Yet, the legacy of these disturbances for future forest development remains unclear. Bark beetle disturbances are expected to increase further because of climate change. Consequently, feedbacks within the disturbance regime are of growing interest, for example, whether bark beetle outbreaks are amplifying future bark beetle activity (through the initiation of an even-aged cohort of trees) or dampening it (through increased structural and compositional diversity).We studied bark beetle-vegetation-climate interactions in the Bavarian Forest National Park (Germany), an area characterised by unprecedented bark beetle activity in the recent past. We simulated the effect of future bark beetle outbreaks on forest structure and composition and analysed how disturbance-mediated forest dynamics influence future bark beetle activity under different scenarios of climate change. We used process-based simulation modelling in combination with machine learning to disentangle the long-term interactions between vegetation, climate and bark beetles at the landscape scale.Disturbances by the European spruce bark beetle were strongly amplified by climate change, increasing between 59% and 221% compared to reference climate. Bark beetle outbreaks reduced the dominance of Norway spruce (Picea abies (L.) Karst.) on the landscape, increasing compositional diversity. Disturbances decreased structural diversity within stands (α diversity) and increased structural diversity between stands (β diversity). Overall, disturbance-mediated changes in forest structure and composition dampened future disturbance activity (a reduction of up to -67%), but were not able to fully compensate for the amplifying effect of climate change. Synthesis. Our findings indicate that the recent disturbance episode at the Bavarian Forest National Park was caused by a convergence of highly susceptible forest structures with climatic conditions favourable for bark beetle outbreaks. While future climate is increasingly conducive to massive outbreaks, the emerging landscape structure is less and less likely to support them. This study improves our understanding of the long-term legacies of ongoing bark beetle disturbances in Central Europe. It indicates that increased diversity provides an important dampening feedback, and suggests that preventing disturbances or homogenizing post-disturbance forests could elevate the future susceptibility to large-scale bark beetle outbreaks.
| S-EPMC7894307 | biostudies-literature
Project description:Bark beetle outbreaks and forest fires have imposed severe ecological damage and caused billions of dollars in lost resources in recent decades. The impact of such combined disturbances is projected to become more severe, especially as climate change takes its toll on forest ecosystems in the coming years. Here, we investigate the impact of multiple disturbances in a demographically heterogeneous tree population, using an age-structured difference equation model of bark beetle outbreaks and forest fires. We identify two dynamical regimes for beetle and fire dynamics. The model predicts that fire helps dampen beetle outbreaks not only by removing host trees but also by altering the demographic structure of forest stands. We show that a stand thinning protocol, which reduces the population size of the largest few juvenile classes by a small percentage, is able to significantly reduce beetle-induced tree mortality. Our research demonstrates one approach to capturing compound disturbances in a mathematical model.
| S-EPMC8683088 | biostudies-literature
Project description:Planning forest management relies on predicting insect outbreaks such as mountain pine beetle, particularly in the intermediate-term future, e.g., 5-year. Machine-learning algorithms are potential solutions to this challenging problem due to their many successes across a variety of prediction tasks. However, there are many subtle challenges in applying them: identifying the best learning models and the best subset of available covariates (including time lags) and properly evaluating the models to avoid misleading performance-measures. We systematically address these issues in predicting the chance of a mountain pine beetle outbreak in the Cypress Hills area and seek models with the best performance at predicting future 1-, 3-, 5- and 7-year infestations. We train nine machine-learning models, including two generalized boosted regression trees (GBM) that predict future 1- and 3-year infestations with 92% and 88% AUC, and two novel mixed models that predict future 5- and 7-year infestations with 86% and 84% AUC, respectively. We also consider forming the train and test datasets by splitting the original dataset randomly rather than using the appropriate year-based approach and show that this may obtain models that score high on the test dataset but low in practice, resulting in inaccurate performance evaluations. For example, a k-nearest neighbor model with the actual performance of 68% AUC, scores the misleadingly high 78% on a test dataset obtained from a random split, but the more accurate 66% on a year-based split. We then investigate how the prediction accuracy varies with respect to the provided history length of the covariates and find that neural network and naive Bayes, predict more accurately as history-length increases, particularly for future 1- and 3-year predictions, and roughly the same holds with GBM. Our approach is applicable to other invasive species. The resulting predictors can be used in planning forest and pest management and planning sampling locations in field studies.
| S-EPMC8495826 | biostudies-literature
Project description:Herein we report the asymmetric syntheses of a number of oxygenated terpenoids that are of importance in the chemical ecology of bark beetles. These are pinocamphones, isopinocamphones, pinocarvones, and 4-thujanols (= sabinene hydrates). The camphones were synthesized from isopinocampheol, the pinocarvones from β-pinene, and the thujanols from sabinene. The NMR spectroscopic data, specific rotations, and elution orders of their stereoisomers on a chiral GC-phase (β-cyclodextrin) are also reported. This enables facile synthesis of pure compounds for biological activity studies and identification of stereoisomers in mixed natural samples.
| S-EPMC7705961 | biostudies-literature
Project description:Understanding disturbance interactions and their ecological consequences remains a major challenge for research on the response of forests to a changing climate. When, where, and how one disturbance may alter the severity, extent, or occurrence probability of a subsequent disturbance is encapsulated by the concept of linked disturbances. Here, we evaluated 1) how climate and forest habitat variables, including disturbance history, interact to drive 2000s spruce beetle (Dendroctonus rufipennis) infestation of Engelmann spruce (Picea engelmannii) across the Southern Rocky Mountains; and 2) how previous spruce beetle infestation affects subsequent infestation across the Flat Tops Wilderness in northwestern Colorado, which experienced a severe landscape-scale spruce beetle infestation in the 1940s. We hypothesized that drought and warm temperatures would promote infestation, whereas small diameter and non-host trees, which may reflect past disturbance by spruce beetles, would inhibit infestation. Across the Southern Rocky Mountains, we found that climate and forest structure interacted to drive the 2000s infestation. Within the Flat Tops study area we found that stands infested in the 1940s were composed of higher proportions of small diameter and non-host trees ca. 60 years later. In this area, the 2000s infestation was constrained by a paucity of large diameter host trees (> 23 cm at diameter breast height), not climate. This suggests that there has not been sufficient time for trees to grow large enough to become susceptible to infestation. Concordantly, we found no overlap between areas affected by the 1940s infestation and the current infestation. These results show a severe spruce beetle infestation, which results in the depletion of susceptible hosts, can create a landscape template reducing the potential for future infestations.
| S-EPMC4441381 | biostudies-literature
Project description:1. Unprecedented bark beetle outbreaks have been observed for a variety of forest ecosystems recently, and damage is expected to further intensify as a consequence of climate change. In Central Europe, the response of ecosystem management to increasing infestation risk has hitherto focused largely on the stand level, while the contingency of outbreak dynamics on large-scale drivers remains poorly understood. 2. To investigate how factors beyond the local scale contribute to the infestation risk from Ips typographus (Col., Scol.), we analysed drivers across seven orders of magnitude in scale (from 103 to 1010 m2) over a 23-year period, focusing on the Bavarian Forest National Park. Time-discrete hazard modelling was used to account for local factors and temporal dependencies. Subsequently, beta regression was applied to determine the influence of regional and landscape factors, the latter characterized by means of graph theory. 3. We found that in addition to stand variables, large-scale drivers also strongly influenced bark beetle infestation risk. Outbreak waves were closely related to landscape-scale connectedness of both host and beetle populations as well as to regional bark beetle infestation levels. Furthermore, regional summer drought was identified as an important trigger for infestation pulses. Large-scale synchrony and connectivity are thus key drivers of the recently observed bark beetle outbreak in the area. 4.Synthesis and applications. Our multiscale analysis provides evidence that the risk for biotic disturbances is highly dependent on drivers beyond the control of traditional stand-scale management. This finding highlights the importance of fostering the ability to cope with and recover from disturbance. It furthermore suggests that a stronger consideration of landscape and regional processes is needed to address changing disturbance regimes in ecosystem management.
| S-EPMC4816203 | biostudies-literature
Project description:Climate change is altering the frequency and severity of forest disturbances such as wildfires and bark beetle outbreaks, thereby increasing the potential for sequential disturbances to interact. Interactions can amplify or dampen disturbances, yet the direction and magnitude of future disturbance interactions are difficult to anticipate because underlying mechanisms remain poorly understood. We tested how variability in postfire forest development affects future susceptibility to bark beetle outbreaks, focusing on mountain pine beetle (Dendroctonus ponderosae) and Douglas-fir beetle (Dendroctonus pseudotsugae) in forests regenerating from the large high-severity fires that affected Yellowstone National Park in Wyoming in 1988. We combined extensive field data on postfire tree regeneration with a well-tested simulation model to assess susceptibility to bark beetle outbreaks over 130 y of stand development. Despite originating from the same fire event, among-stand variation in forest structure was very high and remained considerable for over a century. Thus, simulated emergence of stands susceptible to bark beetles was not temporally synchronized but was protracted by several decades, compared with stand development from spatially homogeneous regeneration. Furthermore, because of fire-mediated variability in forest structure, the habitat connectivity required to support broad-scale outbreaks and amplifying cross-scale feedbacks did not develop until well into the second century after the initial burn. We conclude that variability in tree regeneration after disturbance can dampen and delay future disturbance by breaking spatiotemporal synchrony on the landscape. This highlights the importance of fostering landscape variability in the context of ecosystem management given changing disturbance regimes.
| S-EPMC5135370 | biostudies-literature
Project description:The present project deals with bark beetle gut total proteome from callow and black bark beetle, Ips typographus. The study aims to identify life stage-specific expression of gut proteins in bark beetles and their functional relevance.
2023-11-08 | PXD035407 | Pride
Project description:BackgroundEpitope prediction is a useful approach in cancer immunology and immunotherapy. Many computational methods, including machine learning and network analysis, have been developed quickly for such purposes. However, regarding clinical applications, the existing tools are insufficient because few of the predicted binding molecules are immunogenic. Hence, to develop more potent and effective vaccines, it is important to understand binding and immunogenic potential. Here, we observed that the interactive association constituted by human leukocyte antigen (HLA)-peptide pairs can be regarded as a network in which each HLA and peptide is taken as a node. We speculated whether this network could detect the essential interactive propensities embedded in HLA-peptide pairs. Thus, we developed a network-based deep learning method called DeepNetBim by harnessing binding and immunogenic information to predict HLA-peptide interactions.ResultsQuantitative class I HLA-peptide binding data and qualitative immunogenic data (including data generated from T cell activation assays, major histocompatibility complex (MHC) binding assays and MHC ligand elution assays) were retrieved from the Immune Epitope Database database. The weighted HLA-peptide binding network and immunogenic network were integrated into a network-based deep learning algorithm constituted by a convolutional neural network and an attention mechanism. The results showed that the integration of network centrality metrics increased the power of both binding and immunogenicity predictions, while the new model significantly outperformed those that did not include network features and those with shuffled networks. Applied on benchmark and independent datasets, DeepNetBim achieved an AUC score of 93.74% in HLA-peptide binding prediction, outperforming 11 state-of-the-art relevant models. Furthermore, the performance enhancement of the combined model, which filtered out negative immunogenic predictions, was confirmed on neoantigen identification by an increase in both positive predictive value (PPV) and the proportion of neoantigen recognition.ConclusionsWe developed a network-based deep learning method called DeepNetBim as a pan-specific epitope prediction tool. It extracted the attributes of the network as new features from HLA-peptide binding and immunogenic models. We observed that not only did DeepNetBim binding model outperform other updated methods but the combination of our two models showed better performance. This indicates further applications in clinical practice.
| S-EPMC8097772 | biostudies-literature
Project description:Fish in schooling formations navigate complex flow fields replete with mechanical energy in the vortex wakes of their companions. Their schooling behavior has been associated with evolutionary advantages including energy savings, yet the underlying physical mechanisms remain unknown. We show that fish can improve their sustained propulsive efficiency by placing themselves in appropriate locations in the wake of other swimmers and intercepting judiciously their shed vortices. This swimming strategy leads to collective energy savings and is revealed through a combination of high-fidelity flow simulations with a deep reinforcement learning (RL) algorithm. The RL algorithm relies on a policy defined by deep, recurrent neural nets, with long-short-term memory cells, that are essential for capturing the unsteadiness of the two-way interactions between the fish and the vortical flow field. Surprisingly, we find that swimming in-line with a leader is not associated with energetic benefits for the follower. Instead, "smart swimmer(s)" place themselves at off-center positions, with respect to the axis of the leader(s) and deform their body to synchronize with the momentum of the oncoming vortices, thus enhancing their swimming efficiency at no cost to the leader(s). The results confirm that fish may harvest energy deposited in vortices and support the conjecture that swimming in formation is energetically advantageous. Moreover, this study demonstrates that deep RL can produce navigation algorithms for complex unsteady and vortical flow fields, with promising implications for energy savings in autonomous robotic swarms.
| S-EPMC6003313 | biostudies-literature