A Possible Artificial Intelligence Ecosystem Avatar: the Moorea case
(IDEA)
- URL: http://arxiv.org/abs/2102.02384v1
- Date: Thu, 4 Feb 2021 02:53:55 GMT
- Title: A Possible Artificial Intelligence Ecosystem Avatar: the Moorea case
(IDEA)
- Authors: Jean-Pierre Barriot, Neil Davies, Beno\^it Stoll, S\'ebastien Chabrier
and Alban Gabillon
- Abstract summary: We focus in this paper on a large scale data assimilation and prediction backbone based on Deep Stacking Networks (DSN)
We describe several kinds of raw data that can train and constrain such an ecosystem avatar model, as well as second level data such as ecological or physical indexes / indicators.
- Score: 0.6562256987706128
- License: http://creativecommons.org/licenses/by-nc-nd/4.0/
- Abstract: High-throughput data collection techniques and largescale (cloud) computing
are transforming our understanding of ecosystems at all scales by allowing the
integration of multimodal data such as physics, chemistry, biology, ecology,
fishing, economics and other social sciences in a common computational
framework. We focus in this paper on a large scale data assimilation and
prediction backbone based on Deep Stacking Networks (DSN) in the frame of the
IDEA (Island Digital Ecosystem Avatars) project (Moorea Island), based on the
subdivision of the island in watersheds and lagoon units. We also describe
several kinds of raw data that can train and constrain such an ecosystem avatar
model, as well as second level data such as ecological or physical indexes /
indicators.
Related papers
- Insect Identification in the Wild: The AMI Dataset [35.41544843896443]
Insects represent half of all global biodiversity, yet many of the world's insects are disappearing.
Despite this crisis, data on insect diversity and abundance remain woefully inadequate.
We provide the first large-scale machine learning benchmarks for fine-grained insect recognition.
arXiv Detail & Related papers (2024-06-18T09:57:02Z) - Multiple Random Masking Autoencoder Ensembles for Robust Multimodal
Semi-supervised Learning [64.81450582542878]
There is an increasing number of real-world problems in computer vision and machine learning.
In the case of Earth Observations from satellite data, it is important to be able to predict one observation layer.
arXiv Detail & Related papers (2024-02-12T20:08:58Z) - FREE: The Foundational Semantic Recognition for Modeling Environmental Ecosystems [28.166089112650926]
FREE maps available environmental data into a text space and then converts the traditional predictive modeling task in environmental science to the semantic recognition problem.
When used for long-term prediction, FREE has the flexibility to incorporate newly collected observations to enhance future prediction.
The efficacy of FREE is evaluated in the context of two societally important real-world applications, predicting stream water temperature in the Delaware River Basin and predicting annual corn yield in Illinois and Iowa.
arXiv Detail & Related papers (2023-11-17T00:53:09Z) - SatBird: Bird Species Distribution Modeling with Remote Sensing and
Citizen Science Data [68.2366021016172]
We present SatBird, a satellite dataset of locations in the USA with labels derived from presence-absence observation data from the citizen science database eBird.
We also provide a dataset in Kenya representing low-data regimes.
We benchmark a set of baselines on our dataset, including SOTA models for remote sensing tasks.
arXiv Detail & Related papers (2023-11-02T02:00:27Z) - Semantic Segmentation of Vegetation in Remote Sensing Imagery Using Deep
Learning [77.34726150561087]
We propose an approach for creating a multi-modal and large-temporal dataset comprised of publicly available Remote Sensing data.
We use Convolutional Neural Networks (CNN) models that are capable of separating different classes of vegetation.
arXiv Detail & Related papers (2022-09-28T18:51:59Z) - Conditioned Human Trajectory Prediction using Iterative Attention Blocks [70.36888514074022]
We present a simple yet effective pedestrian trajectory prediction model aimed at pedestrians positions prediction in urban-like environments.
Our model is a neural-based architecture that can run several layers of attention blocks and transformers in an iterative sequential fashion.
We show that without explicit introduction of social masks, dynamical models, social pooling layers, or complicated graph-like structures, it is possible to produce on par results with SoTA models.
arXiv Detail & Related papers (2022-06-29T07:49:48Z) - Unlocking the potential of deep learning for marine ecology: overview,
applications, and outlook [8.3226670069051]
This paper aims to bridge the gap between marine ecologists and computer scientists.
We provide insight into popular deep learning approaches for ecological data analysis in plain language.
We illustrate challenges and opportunities through established and emerging applications of deep learning to marine ecology.
arXiv Detail & Related papers (2021-09-29T21:59:16Z) - Probabilistic modeling of lake surface water temperature using a
Bayesian spatio-temporal graph convolutional neural network [55.41644538483948]
We propose to aggregate simulations of lake temperature at a certain depth together with a range of meteorological features.
This work demonstrates that the proposed model can deliver homogeneously good performance covering the whole lake surface.
Results are compared with a state-of-the-art Bayesian deep learning method.
arXiv Detail & Related papers (2021-09-27T09:19:53Z) - A Digital Forensics Investigation of a Smart Scale IoT Ecosystem [0.0]
Internet of Things (IoT) ecosystems contain residual data, which can be used as digital evidence in court proceedings.
One of these problems is the limited availability of practical processes and techniques to guide the preservation and analysis of residual data from these ecosystems.
We present an empirical demonstration of practical techniques to recover residual data from different evidence sources within a smart scale ecosystem.
arXiv Detail & Related papers (2021-09-12T13:47:17Z) - Dive into Layers: Neural Network Capacity Bounding using Algebraic
Geometry [55.57953219617467]
We show that the learnability of a neural network is directly related to its size.
We use Betti numbers to measure the topological geometric complexity of input data and the neural network.
We perform the experiments on a real-world dataset MNIST and the results verify our analysis and conclusion.
arXiv Detail & Related papers (2021-09-03T11:45:51Z) - StatEcoNet: Statistical Ecology Neural Networks for Species Distribution
Modeling [8.534315844706367]
This paper focuses on a core task in computational sustainability and statistical ecology: species distribution modeling (SDM)
In SDM, the occurrence pattern of a species on a landscape is predicted by environmental features based on observations at a set of locations.
To address the unique challenges of SDM, this paper proposes a framework called StatEcoNet.
arXiv Detail & Related papers (2021-02-17T02:19:00Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.