scholarly journals Focused small-scale fisheries as complex systems using deep learning models

2021 ◽  
Vol 49 (2) ◽  
pp. 342-353
Author(s):  
Ricardo Cavieses-Núñez ◽  
Miguel A. Ojeda-Ruiz ◽  
Alfredo Flores-Irigollen ◽  
Elvia Marín-Monroy ◽  
Mirtha Lbañez-Lucero ◽  
...  
Keyword(s):  
Deep Learning ◽  
Environmental Variables ◽  
Predictive Power ◽  
Small Scale ◽  
Learning Models ◽  
Small Scale Fisheries ◽  
Productive Activities ◽  
Lack Of Information ◽  
Management Measures ◽  
The Face

Small-scale fishing (SSF) is a relevant economic activity worldwide, so sustainable development will be essential to assure its contributions to food security, poverty alleviation, and healthy ecosystems. However, the wide diversity of fisheries, their complexity, and the lack of information limit the ability to propose/evaluate management measures and plans and their effects on communities and other productive activities. The state of Baja California Sur, Mexico, our study case, ranks as the third place in national fisheries production, possesses SSF fleets, has a wide variety of fisheries that share fishing areas, fishing seasons, and operating units. In this work, assuming SSF as a complex system were proposed deep learning models (DLM) to forecast the catch volumes, evaluate each input variable's importance, and find interactions. Environmental variables and catch fisheries were tested in the DLM to estimate their predictive power. Different DLM structures and parameters to find the optimal model was used. The variables that presented higher predictive power are the environmental variables with R = 0.90. Moreover, when used in combination with the catches from other areas, the performance of R = 0.95 is obtained. Using only the catches, the model has an R = 0.81. This model allows the use of variables that indirectly affect the system and demonstrates a useful tool to assess a complex system's state in the face of disturbances in its variables.

scholarly journals Deep learning models for the prediction of small-scale fisheries catches: finfish fishery in the region of “Bahía Magadalena-Almejas”

2018 ◽  
Vol 75 (6) ◽  
pp. 2088-2096 ◽  
Author(s):  
Ricardo Alberto Cavieses Núñez ◽  
Miguel Ángel Ojeda Ruiz de la Peña ◽  
Alfredo Flores Irigollen ◽  
Manuel Rodríguez Rodríguez
Keyword(s):  
Deep Learning ◽  
Short Term Memory ◽  
Low Cost ◽  
Small Scale ◽  
Learning Models ◽  
Small Scale Fisheries ◽  
Relevant Role ◽  
Important Challenge ◽  
Memory Network ◽  
Using Data

Abstract Globally, over 80% of fisheries are at maximum sustainable levels or overexploited. However, small-scale fisheries (SSFs) in developing countries play a relevant role in coastal communities’ development with important impacts on the economy. The SSFs are normally multi-specific and due to the lack of data, studying them by simulation poses an important challenge especially forecasting models. These models are necessary to support management decisions or develop sustainable fisheries; therefore, models based on Deep Learning were proposed to forecast SSFs catch, using data from official catch landing reports (OCLRs), satellite images, and oceanographic data. The finfish fishery in Bahía Magdalena-Almejas (México) was used for the present study. According to an analysis of OCLRs, the target species of major importance in the fishery were identified and selected for the model. The proposed deep learning models used two artificial neural networks structures: non-linear autoregressive neural network and long-short term memory network, which were designed to assess and forecast monthly catch levels of Paralabrax nebulifer and Caulolatilus princeps. Models with a performance efficiency of R > 0.8, MSE < 300 were found, which indicate that the models are applicable in SSF with poor data and multi-specific fishery contexts, at low cost.

scholarly journals The Importance of Values in Predicting and Encouraging Environmental Behavior: Reflections From a Costa Rican Small-Scale Fishery

2021 ◽  
Vol 8 ◽  
Author(s):  
Astrid Sánchez-Jiménez ◽  
Douglas MacMillan ◽  
Matthias Wolff ◽  
Achim Schlüter ◽  
Marie Fujitani
Keyword(s):  
Fisheries Management ◽  
Behavioral Intentions ◽  
Survey Design ◽  
Environmental Behavior ◽  
Ecosystem Modeling ◽  
Control Treatment ◽  
Small Scale ◽  
Perceived Behavioral Control ◽  
Small Scale Fisheries ◽  
Management Measures

Encouraging people’s pro-environmental behaviors is an objective of Education for Sustainable Development. In the context of small-scale fisheries, unsustainable fishing practices are compromising the integrity of coastal communities and ecosystems. Ecopath with Ecosim (EwE) is an ecosystem modeling software that presents interactions/changes in the food web as a result of fishing. Despite the multiple applications of EwE in fisheries management, it is unknown from a quantitative perspective whether the application of EwE trophic modeling in environmental education processes and management produces effects on norms and ecological beliefs, and if it alters behavioral intentions of the participants receiving ecosystem modeling information. We conducted a behavior change intervention with gillnet fishers in the Gulf of Nicoya, Costa Rica, to compare antecedents of pro-environmental behavior between participants who received an ecosystem-based intervention (lectures containing EwE models; treatment) and those who received lectures that didn’t involve EwE (control). Based on theories of environmental psychology, we used a pre–post survey design, to evaluate changes between control/treatment, and to assess the influence of psychometric constructs and fishing characteristics on the behavioral intentions to support sustainable fishing measures and owning a fishing license (revealed behavior). Personal norms and values were significant at explaining management measures’ support, along with some fishing characteristics (e.g., fishing site). Deliberating about possible future scenarios (via EwE-modeling) helped reduce uncertainties, increasing legitimacy and a perceived behavioral control (PBC) to support measures. Currently, licenses in the Gulf aren’t granted under defined ecological criteria, and although altruistic-biospheric values scored highly before the intervention began, due to mistrust and high illegal-unlicensed fishing, fishers may be underestimating how much others care about the environment. Value-oriented and ecosystem-based interventions may assist to effectively redesign the licensing system and encourage fishers to support sustainable measures. Our research indicates the importance of education interventions that teach about the impacts of fishing in the ecosystem while helping participants to perceive themselves as capable of implementing actions (PBC) and expressing biospheric-altruistic values to restore trust. Redirecting human behaviors to reconnect with ecosystem resilience can be a leverage point for sustainability and for the compliance of small-scale fisheries management measures.

scholarly journals Ani-GIFs: A Benchmark Dataset for Domain Generalization of Action Recognition from GIFs

2021 ◽  
Author(s):  
Shoumik Majumdar ◽  
Shubhangi Jain ◽  
Isidora Chara Tourni ◽  
Arsenii Mustafin ◽  
Diala Lteif ◽  
...  
Keyword(s):  
Deep Learning ◽  
Data Acquisition ◽  
Action Recognition ◽  
Data Augmentation ◽  
Learning Models ◽  
Visual Content ◽  
Lack Of Information ◽  
Temporal Features ◽  
Synthetic Video ◽  
Multiple Domains

Deep learning models perform remarkably well for the same task under the assumption that data is always coming from the same distribution. However, this is generally violated in practice, mainly due to the differences in the data acquisition techniques and the lack of information about the underlying source of new data. Domain Generalization targets the ability to generalize to test data of an unseen domain; while this problem is well-studied for images, such studies are significantly lacking in spatiotemporal visual content – videos and GIFs. This is due to (1) the challenging nature of misalignment of temporal features and the varying appearance/motion of actors and actions in different domains, and (2) spatiotemporal datasets being laborious to collect and annotate for multiple domains. We collect and present the first synthetic video dataset of Animated GIFs for domain generalization, Ani-GIFs, that is used to study domain gap of videos vs. GIFs, and animated vs. real GIFs, for the task of action recognition. We provide a training and testing setting for Ani-GIFs, and extend two domain generalization baseline approaches, based on data augmentation and explainability, to the spatiotemporal domain to catalyze research in this direction.

scholarly journals Factors Influencing Small-Scale Fishers’ Individual Perceived Wellbeing Satisfaction in Southern Benin

2021 ◽  
Vol 13 (11) ◽  
pp. 6279
Author(s):  
Sètondji Ben-Vital Kolawolé Kpanou ◽  
Houinsou Dedehouanou ◽  
Sylvain Kpenavoun Chogou ◽  
Augustin K. N. Aoudji ◽  
Thomas Dogot
Keyword(s):  
Property Rights ◽  
The State ◽  
Water Bodies ◽  
Small Scale ◽  
Daily Lives ◽  
Public Managers ◽  
Factors Influencing ◽  
Management Measures ◽  
The Face ◽  
Southern Benin

In southern Benin, the rapid growth of demographics and the need for fishery products have forced public managers to adopt various management measures in the face of anti-ecological methods used by fishers; however, these strategies are often formulated independent from the context. These measures have not remained without consequence on the daily lives of fishers. This paper examines factors influencing fishers’ individual perceived wellbeing satisfaction using the social-ecological system framework. Data on 205 small-scale fishers’ demographic information, perception of job, and individual wellbeing satisfaction and governance subsystems were collected and analysed by the use of an ordered logistic regression. The results demonstrate that job satisfaction and ownership of water bodies (in contradiction to Ostrom’s advocation for commons management) affected fishers’ individual perceived wellbeing satisfaction. Fishers likely value ownerships, affecting their perceived wellbeing mainly in the South East. The prohibition of certain fishing gear decreases fishers’ individual perceived wellbeing, indicating their attachment to these. Therefore, the question remains as to whether or not the scenarios of eco-sustainability of artisanal fisheries can be managed in the same manner as those related urban dwellers and the public sector. This is in particular reference to the line between urban land property rights, urban dwellers and the state, and property rights on water bodies, fishers, and the state.

scholarly journals On the relationship between squid and the environment: artisanal jigging for Loligo plei at São Sebastião Island (24°S), southeastern Brazil

2010 ◽  
Vol 67 (7) ◽  
pp. 1353-1362 ◽  
Author(s):  
Felippe A. Postuma ◽  
Maria A. Gasalla
Keyword(s):  
Environmental Variables ◽  
Linear Models ◽  
Environmental Data ◽  
Southeastern Brazil ◽  
Small Scale ◽  
Lunar Phase ◽  
Catch Per Unit Effort ◽  
Chl A ◽  
Small Scale Fisheries ◽  
The Relationship

AbstractPostuma, F. A., and Gasalla, M. A. 2010. On the relationship between squid and the environment: artisanal jigging for Loligo plei at São Sebastião Island (24°S), southeastern Brazil. – ICES Journal of Marine Science, 67: 1353–1362. The squid Loligo plei concentrates in the southeastern Brazil Bight, where it has traditionally supported small-scale fisheries around São Sebastião Island (SSI). Sea surface temperature (SST), chlorophyll-a (Chl a), windspeed, wave height, rainfall, and lunar phase are related to fishing records and to the results of a survey of local fishers to investigate how they believe environmental variables might affect catches of L. plei. Daily fishery-dependent data over the years 2005–2009 were obtained from a fishing cooperative and were matched with satellite and meteorological forecast data. Generalized linear models were used to explore the significance of environmental variables in relation to variability in catch and catch per unit effort (cpue). Squid are fished with jigs in water shallower than 20 m, generally where SST is warmer and Chl a and windspeed are lower. Cpue and monthly catches decreased from 2005 to 2008, followed by a slight increase in 2009. The correlations between fishery and environmental data relate well to fishers' oceanological knowledge, underscoring the potential of incorporating such knowledge into evaluations of the fishery.

scholarly journals Face Reconstruction with Variational Autoencoder and Face Masks

2021 ◽  
Author(s):  
Rafael S. Toledo ◽  
Eric A. Antonelo
Keyword(s):  
Deep Learning ◽  
Face Mask ◽  
Loss Functions ◽  
High Dimensional ◽  
Learning Models ◽  
Face Reconstruction ◽  
Variational Autoencoder ◽  
The Face ◽  
Face Synthesis

Variational AutoEncoders (VAE) employ deep learning models to learn a continuous latent z-space that is subjacent to a high-dimensional observed dataset. With that, many tasks are made possible, including face reconstruction and face synthesis. In this work, we investigated how face masks can help the training of VAEs for face reconstruction, by restricting the learning to the pixels selected by the face mask. An evaluation of the proposal using the celebA dataset shows that the reconstructed images are enhanced with the face masks, especially when SSIM loss is used either with l1 or l2 loss functions. We noticed that the inclusion of a decoder for face mask prediction in the architecture affected the performance for l1 or l2 loss functions, while this was not the case for the SSIM loss. Besides, SSIM perceptual loss yielded the crispest samples between all hypotheses tested, although it shifts the original color of the image, making the usage of the l1 or l2 losses together with SSIM helpful to solve this issue.

scholarly journals An Automated Framework for Patient Identification and Verification Using Deep Learning

2020 ◽  
Vol 34 (6) ◽  
pp. 709-719
Author(s):  
Suresh Tommandru ◽  
Domnic Sandanam
Keyword(s):  
Deep Learning ◽  
Contrast Enhancement ◽  
Real Time ◽  
Detection System ◽  
Medical Emergency ◽  
Light Illumination ◽  
Learning Models ◽  
Patient Identification ◽  
Illumination Problem ◽  
The Face

Automated patient identification and verification are very important at a medical emergency and when patients are not carrying his/her identity. It is a risk factor that identifying the correct patient identity for doctors to provide medical treatment. The majority of the identification or verification is being done by wristbands, RFID tags, fingerprint, face detection by using handcraft feature-based face recognition systems. A new framework based on robust deep learning model and contrast enhancement is proposed in this paper. In the proposed work, the light illumination problem has been addressed by the contrast enhancement technique for deep learning models to recognize the face. It is proved that the inclusion of contrast enhancement is improving patient identification and verification. To evaluate the deep learning framework, the proposed deep learning models have been trained on our own dataset and have been tested with a real-time medical providing agency. The experimental results show that the proposed framework exhibits more robust test results with accuracy than existing hand-crafted techniques under the live webcam video capture for the real-time patient detection system.

Development of risk assessment model for groundwater level by wavelet-deep learning approach with smart pumping data 

2021 ◽  
Author(s):  
Tsai-Ning Weng ◽  
Chu-Chun Hsu ◽  
Yuan-Chien Lin
Keyword(s):  
Risk Assessment ◽  
Deep Learning ◽  
Wavelet Transform ◽  
Water Level ◽  
Groundwater Level ◽  
Groundwater Resources ◽  
Assessment Model ◽  
Small Scale ◽  
Time Lags ◽  
Learning Models

<p><strong>Abstract</strong></p><p>Groundwater, as a vital existence in human life and economic development, is also one of the stable sources of water resources. Therefore, how to properly utilize groundwater becomes a very important issue when faced with water shortages. However, most of the previous literature uses monthly data as the time scale, and usually uses the historical water level data of the area as the only input factor in the modeling process without considering pumping information and rainfall. This shows that the current studies of small-scale data which is based on the use of multiple factors with hydrological mechanisms to explore and predict the groundwater level is still quite lacking.</p><p>Therefore, this study proposed a novel framework combining wavelet analysis and deep learning models called wavelet-deep learning models and taking the Daliao area of ​​Kaohsiung as an example. From the historical hourly observation data during 2017/08/23-2020/01/30, including groundwater level, smart pumping measurement, tidal, and meteorological data. After abstracting important features of each factor with groundwater level by wavelet transform, using deep learning algorithms such as recurrent neural networks (RNN) and long short-term memory (LSTM) model to summarize and predict the impact of multiple variable factors on the groundwater level under different time lags. The results of hourly prediction show that the performance of the LSTM model and RNN model are both reliable in which values of the coefficient of determination () were obtained 0.813 and 0.784, respectively.</p><p>This study provides a feasible and accurate approach for groundwater level prediction by understanding and predicting different water level changes that may occur in the Daliao area in advance. As a result, the study will be an important reference for groundwater resources management and risk assessment, and achieve the goal of sustainable use of groundwater resources.</p><p> </p><p><strong>Keywords </strong>Groundwater prediction, Wavelet transform,<strong> </strong>Risk assessment, LSTM</p>

scholarly journals Sustainability, Disaster Risk Reduction and Climate Change Adaptation: Building from the Bottom Up – A South African Perspective from the Small-scale Fisheries Sector

2021 ◽  
pp. 151-181
Author(s):  
Merle Sowman ◽  
Xavier Rebelo
Keyword(s):  
Climate Change ◽  
South Africa ◽  
Sustainable Development ◽  
National Level ◽  
Small Scale ◽  
Small Scale Fisheries ◽  
The Face ◽  
Government Planning ◽  
Decision Making Processes ◽  
Policy Alignment

AbstractThis chapter explores the vulnerability context of coastal fishing communities, including the various factors that shape their capacity to cope with and adapt in the face of poverty and increasing threats associated with climate change and natural and human-induced disasters through the lens of small-scale fisheries (SSFs) in South Africa. South Africa has developed a suite of policies, strategies and laws to deal with commitments to sustainable development and address and manage climate change challenges and disaster risks. These national policies, however, are not well aligned or implemented in a coordinated and integrated manner. Nor are they attuned to the realities facing local communities. This chapter reports on work in coastal communities in South Africa that reveals the lack of policy alignment and limited coordination across government departments at all levels charged with oversight responsibilities for these endeavours. Findings suggest that incorporating local knowledge into local development and sector plans, as well as into sustainable development and sector-specific policies, strategies and plans at the national level, would enhance understanding of the realities on the ground and lead to policies, strategies and plans that are more harmonised and more likely to be supported and implemented. How this knowledge gets integrated both vertically and horizontally into formal government planning and decision-making processes, however, and leads to implementation of projects and plans that yield tangible results, remains a challenge.

Sign in / Sign up

Export Citation Format

Share Document