Agrodiversity v.2: An educational simulation tool to address some challenges for sustaining functional agrodiversity in agro-ecosystems

Functional agrodiversity can be useful and even essential for, i.e., the long-term sustainability of agriculture. However, still many aspects of this concept are not well understood. The interplay between species in diverse agro-ecosystems is based on processes as, i.e., competition, facilitation, and predator-prey relations. The net-effect of these processes on crop growth is not static and can change over time as the relative density of species change. The equilibrium state of a diverse agro-ecosystem might be far from optimum or even unproductive. This makes agrodiveristy a concept which is not easily grasped nor obtained or maintained. We believe that an agent-based model can facilitate learning on the topic of functional agrodiversity. In this paper, we present the agent-based simulation model, Agrodiversity v.2, developed in Netlogo 3.1.5. The model simulates a virtual diverse agro-ecosystem with four ecological agents. The user is challenged to explore ecological parameters and design a productive sustainable system. The model's “simplest playing level” shows that a proper balance between the co-existing species is necessary so that their ecological interactions allow the multi-species system to become self-organized and persist over time. It demonstrates the transient nature of profitable functional agrodiversity. Our analysis on the effects of using Agrodiversity v.2 on actual learning shows that the learning took place. Students increased the quality of their answers to paper-based individual questions on the topic from 29% during passive/conceptual teaching to 86% after the simulation session. On average students stated to have learnt 55% of their current knowledge through the workshop of which 76% was learnt by using the simulation.     

Automated detection of frog calls and choruses by pulse repetition rate

Anurans (frogs and toads) are among the most globally threatened taxonomic groups. Successful conservation of anurans will rely on improved data on the status and changes in local populations, particularly for rare and threatened species. Automated sensors, such as acoustic recorders, have the potential to provide such data by massively increasing the spatial and temporal scale of population sampling efforts. Analyzing such data sets will require robust and efficient tools that can automatically identify the presence of a species in audio recordings. Like bats and birds, many anuran species produce distinct vocalizations that can be captured by autonomous acoustic recorders and represent excellent candidates for automated recognition. However, in contrast to birds and bats, effective automated acoustic recognition tools for anurans are not yet widely available. An effective automated call-recognition method for anurans must be robust to the challenges of real-world field data and should not require extensive labeled data sets. We devised a vocalization identification tool that classifies anuran vocalizations in audio recordings based on their periodic structure: the repeat interval-based bioacoustic identification tool (RIBBIT). We applied RIBBIT to field recordings to study the boreal chorus frog (Pseudacris maculata) of temperate North American grasslands and the critically endangered variable harlequin frog (Atelopus varius) of tropical Central American rainforests. The tool accurately identified boreal chorus frogs, even when they vocalized in heavily overlapping choruses and identified variable harlequin frog vocalizations at a field site where it had been very rarely encountered in visual surveys. Using a few simple parameters, RIBBIT can detect any vocalization with a periodic structure, including those of many anurans, insects, birds, and mammals. We provide open-source implementations of RIBBIT in Python and R to support its use for other taxa and communities.     

Learning from the rubble: the case of Christchurch,New Zealand,after the 2010 and 2011 earthquakes

Learning after a disaster is crucial in creating more resilient places. However, many societies are repeatedly overwhelmed by disasters. This can be because of missed opportunities to learn in post‐disaster settings or because of actions implemented that seem to be highly relevant to recovery in the short term, but potentially constrain aspirations in the longer term. This paper assesses learning processes among state and non‐state actors and the ways in which these are bridged and scaled up to wider improvements in governance. Aiming to enrich understanding of post‐disaster learning, it explores different actors’ response actions after the earthquakes in Christchurch, New Zealand, in 2010 and 2011. On the one hand, ‘learning by doing’ is occurring, yet, on the other hand, systemic learning is hindered by mismatches between top‐down steering and bottom‐up initiatives. The study concludes that better linking and synergising of learning processes among different levels is vital for enhancing resilience in post‐disaster societies.     

火炸药企业重大事故隐患危险性评估的计算机自学习实现

通过对火炸药工厂重大事故隐患危险性评估方法的分析,以计算机自学习的基本结构为主线,详细探讨了以机械学习策略完成该评估程序中对新危险品源自学习的过程。对此过程中知识表示等几个应注意的问题进行了描述     

Grasslands, People, and Conservation: Over-the-Horizon Learning Exchanges between African and American Pastoralists

Abstract:  The world's grasslands and large migratory populations of wildlife have been disproportionately lost or disrupted by human activities, yet are poorly represented in protected areas. The major threats they face are land subdivision and the loss of large-scale dynamic processes such as wildlife migrations and fire. The large-scale dynamical processes and ubiquity of livestock economies and cultures across the grasslands calls for an integrated ecosystem approach to conservation to make up the shortfall in protected-area coverage. Ranchers and pastoralists will be more inclined to adopt an integrated landscape approach to conservation if they also see the threats to wildlife and grassland ecosystems as affecting their livelihoods and way of life. We arranged a series of learning exchanges between African and American pastoralists, ranchers, scientists, and conservationists aimed at building the collaboration and consensus needed to conserve grasslands at a landscape level. There was broad agreement on the threat of land fragmentation to livelihoods, wildlife, and grasslands. The exchanges also identified weaknesses in prevailing public, private, and community modes of ownership in halting fragmentation. New collaborative approaches were explored to attain the benefits of privatization while keeping the landscape open. The African–U.S. exchanges showed that learning exchanges can anticipate over-the-horizon problems and speed up the feedback loops that underlie adaptive management and build social and ecological resilience.     

Butterfly effects in mimicry? Combining signal and taste can twist the relationship of Müllerian co-mimics

Müllerian co-mimics are aposematic species that resemble each other; sharing a warning signal is thought to be mutually beneficial for the co-mimics by reducing per capita predation risk. In Batesian mimicry, edible mimics avoid predation by resembling an aposematic model species. The protection of both the model and the mimic is weakened when the mimics are abundant compared to the models. The quasi-Batesian view suggests that defended (Müllerian) co-mimics, when unequal in their defences, could also show a Batesian-like trend of increasing mortality with increasing abundance of a less defended “mimic”. We manipulated frequencies of unequally distasteful artificial co-mimics that were prey for great tits. The co-mimics had different signals (imperfect mimicry) but were equally preferred by the birds when palatable. Unexpectedly, when unpalatable, one of the signals was easier for the birds to learn to avoid. Consequently, during predator learning, the signal design of the prey strongly affected mortality of the co-mimics; there was an interaction between the signal and frequency treatments, but increasing the frequency of a less defended “mimic” did not increase co-mimic mortalities as predicted. In contrast, in a memory test that followed, the effect of signal design disappeared; if the birds had experienced high frequency of “mimics” during learning, co-mimic mortalities did subsequently increase. Since the effect of co-mimic frequencies on mortalities changed depending on the signal design of the prey and predator experience, the results suggest that mimetic relationship may be an unpredictable interplay of several factors in addition to taste and abundance.     

Catalyzing success in community-based conservation

Efforts to devolve rights and engage Indigenous Peoples and local communities in conservation have increased the demand for evidence of the efficacy of community-based conservation (CBC) and insights into what enables its success. We examined the human well-being and environmental outcomes of a diverse set of 128 CBC projects. Over 80% of CBC projects had some positive human well-being or environmental outcomes, although just 32% achieved positive outcomes for both (i.e., combined success). We coded 57 total national-, community-, and project-level variables and controls from this set, performed random forest classification to identify the variables most important to combined success, and calculated accumulated local effects to describe their individual influence on the probability of achieving it. The best predictors of combined success were 17 variables suggestive of various recommendations and opportunities for conservation practitioners related to national contexts, community characteristics, and the implementation of various strategies and interventions informed by existing CBC frameworks. Specifically, CBC projects had higher probabilities of combined success when they occurred in national contexts supportive of local governance, confronted challenges to collective action, promoted economic diversification, and invested in various capacity-building efforts. Our results provide important insights into how to encourage greater success in CBC.     

Introducing a common taxonomy to support learning from failure in conservation

Although some sectors have made significant progress in learning from failure, there is currently limited consensus on how a similar transition could best be achieved in conservation and what is required to facilitate this. One of the key enabling conditions for other sectors is a widely accepted and standardized classification system for identifying and analyzing root causes of failure. We devised a comprehensive taxonomy of root causes of failure affecting conservation projects. To develop this, we solicited examples of real-life conservation efforts that were deemed to have failed in some way, identified their underlying root causes of failure, and used these to develop a generic, 3-tier taxonomy of the ways in which projects fail, at the top of which are 6 overarching cause categories that are further divided into midlevel cause categories and specific root causes. We tested the taxonomy by asking conservation practitioners to use it to classify the causes of failure for conservation efforts they had been involved in. No significant gaps or redundancies were identified during this testing phase. We then analyzed the frequency that particular root causes were encountered by projects within this test sample, which suggested that some root causes were more likely to be encountered than others and that a small number of root causes were more likely to be encountered by projects implementing particular types of conservation action. Our taxonomy could be used to improve identification, analysis, and subsequent learning from failed conservation efforts, address some of the barriers that currently limit the ability of conservation practitioners to learn from failure, and contribute to establishing an effective culture of learning from failure within conservation.     

Spatial prediction of soil contamination based on machine learning: a review

● A review of machine learning (ML) for spatial prediction of soil contamination. ● ML have achieved significant breakthroughs for soil contamination prediction. ● A structured guideline for using ML in soil contamination is proposed. ● The guideline includes variable selection, model evaluation, and interpretation. Soil pollution levels can be quantified via sampling and experimental analysis; however, sampling is performed at discrete points with long distances owing to limited funding and human resources, and is insufficient to characterize the entire study area. Spatial prediction is required to comprehensively investigate potentially contaminated areas. Consequently, machine learning models that can simulate complex nonlinear relationships between a variety of environmental conditions and soil contamination have recently become popular tools for predicting soil pollution. The characteristics, advantages, and applications of machine learning models used to predict soil pollution are reviewed in this study. Satisfactory model performance generally requires the following: 1) selection of the most appropriate model with the required structure; 2) selection of appropriate independent variables related to pollutant sources and pathways to improve model interpretability; 3) improvement of model reliability through comprehensive model evaluation; and 4) integration of geostatistics with the machine learning model. With the enrichment of environmental data and development of algorithms, machine learning will become a powerful tool for predicting the spatial distribution and identifying sources of soil contamination in the future.     

State-of-the-art applications of machine learning in the life cycle of solid waste management

● State-of-the-art applications of machine learning (ML) in solid waste (SW) is presented. ● Changes of research field over time, space, and hot topics were analyzed. ● Detailed application seniors of ML on the life cycle of SW were summarized. ● Perspectives towards future development of ML in the field of SW were discussed. Due to the superiority of machine learning (ML) data processing, it is widely used in research of solid waste (SW). This study analyzed the research and developmental progress of the applications of ML in the life cycle of SW. Statistical analyses were undertaken on the literature published between 1985 and 2021 in the Science Citation Index Expanded and Social Sciences Citation Index to provide an overview of the progress. Based on the articles considered, a rapid upward trend from 1985 to 2021 was found and international cooperatives were found to have strengthened. The three topics of ML, namely, SW categories, ML algorithms, and specific applications, as applied to the life cycle of SW were discussed. ML has been applied during the entire SW process, thereby affecting its life cycle. ML was used to predict the generation and characteristics of SW, optimize its collection and transportation, and model the processing of its energy utilization. Finally, the current challenges of applying ML to SW and future perspectives were discussed. The goal is to achieve high economic and environmental benefits and carbon reduction during the life cycle of SW. ML plays an important role in the modernization and intellectualization of SW management. It is hoped that this work would be helpful to provide a constructive overview towards the state-of-the-art development of SW disposal.