Successes and Challenges from Formation to Implementation of Eleven Broad‐Extent Conservation Programs

Integration of conservation partnerships across geographic, biological, and administrative boundaries is increasingly relevant because drivers of change, such as climate shifts, transcend these boundaries. We explored successes and challenges of established conservation programs that span multiple watersheds and consider both social and ecological concerns. We asked representatives from a diverse set of 11 broad‐extent conservation partnerships in 29 countries 17 questions that pertained to launching and maintaining partnerships for broad‐extent conservation, specifying ultimate management objectives, and implementation and learning. Partnerships invested more funds in implementing conservation actions than any other aspect of conservation, and a program's context (geographic extent, United States vs. other countries, developed vs. developing nation) appeared to substantially affect program approach. Despite early successes of these organizations and benefits of broad‐extent conservation, specific challenges related to uncertainties in scaling up information and to coordination in the face of diverse partner governance structures, conflicting objectives, and vast uncertainties regarding future system dynamics hindered long‐term success, as demonstrated by the focal organizations. Engaging stakeholders, developing conservation measures, and implementing adaptive management were dominant challenges. To inform future research on broad‐extent conservation, we considered several challenges when we developed detailed questions, such as what qualities of broad‐extent partnerships ensure they complement, integrate, and strengthen, rather than replace, local conservation efforts and which adaptive management processes yield actionable conservation strategies that account explicitly for dynamics and uncertainties regarding multiscale governance, environmental conditions, and knowledge of the system? Éxitos y Retos de la Formación a la Implementación de Once Programas de Conservación de Amplio Alcance     

A systematic survey of the integration of animal behavior into conservation

The role of behavioral ecology in improving wildlife conservation and management has been the subject of much recent debate. We sought to answer 2 foundational questions about the current use of behavioral knowledge in conservation: To what extent is behavioral knowledge used in wildlife conservation and management, and how does the use of animal behavior differ among conservation fields in both frequency and types of use? We searched the literature for intersections between key fields of animal behavior and conservation and created a systematic heat map (i.e., graphical representation of data where values are represented as colors) to visualize relative efforts. Some behaviors, such as dispersal and foraging, were commonly considered (mean [SE] of 1147.38 [353.11] and 439.44 [108.85] papers per cell, respectively). In contrast, other behaviors, such as learning, social, and antipredatory behaviors were rarely considered (mean [SE] of 33.88 [7.62], 44.81 [10.65], and 22.69 [6.37] papers per cell, respectively). In many cases, awareness of the importance of behavior did not translate into applicable management tools. Our results challenge previous suggestions that there is little association between the fields of behavioral ecology and conservation and reveals tremendous variation in the use of different behaviors in conservation. We recommend that researchers focus on examining underutilized intersections of behavior and conservation themes for which preliminary work shows a potential for improving conservation and management, translating behavioral theory into applicable and testable predictions, and creating systematic reviews to summarize the behavioral evidence within the behavior‐conservation intersections for which many studies exist.     

The role of agent-based models in wildlife ecology and management

Conservation planning of critical habitats for wildlife species at risk is a priority topic that requires the knowledge of how animals select and use their habitat, and how they respond to future developmental changes in their environment. This paper explores the role of a habitat-modeling methodological approach, agent-based modeling, which we advocate as a promising approach for ecological research. Agent-based models (ABMs) are capable of simultaneously distinguishing animal densities from habitat quality, can explicitly represent the environment and its dynamism, can accommodate spatial patterns of inter- and intra-species mechanisms, and can explore feedbacks and adaptations inherent in these systems. ABMs comprise autonomous, individual entities; each with dynamic, adaptive behaviors and heterogeneous characteristics that interact with each other and with their environment. These interactions result in emergent outcomes that can be used to quantitatively examine critical habitats from the individual- to population-level. ABMs can also explore how wildlife will respond to potential changes in environmental conditions, since they can readily incorporate adaptive animal-movement ecology in a changing landscape. This paper describes the necessary elements of an ABM developed specifically for understanding wildlife habitat selection, reviews the current empirical literature on ABMs in wildlife ecology and management, and evaluates the current and future roles these ABMs can play, specifically with regards to scenario planning of designated critical habitats.     

Lenses for learning: visual techniques in natural resource management

In this study, we explored the use of selected visual techniques (e.g. video, photography, diagramming) in facilitating learning among Indigenous communities living in remote protected areas at sites in Vietnam and Australia. The techniques were employed during interviews and workshops aimed at accessing and enhancing local peoples' perspectives on their landscape and on specific natural resource management issues. The effectiveness of the different techniques for enabling learning varied markedly with the context, highlighting the need for facilitator skill and flexibility in application of techniques. Visual techniques helped to engage participants; encourage unrestrained and lateral thinking; provide opportunities for self-expression and reflection; and to expose participants to perspectives of other community members. Valuable insights emerged on broad aspects of learning and these were incorporated into a simple model that highlights three types of conceptualisation found to be important in these processes.     

基于SSD网络的电梯内电动自行车检测研究*

为减少因电动自行车违规操作而造成的消防安全事故,杜绝电动自行车进电梯的违规行为,基于深度学习SSD目标检测网络,使用VGG16、EfficientNet、MobileNet 3种主干网络,研究SSD网络对电梯内电动自行车检测的可行性,分析比较3种网络的检测效果,并提出基于双摄的检测方法,进一步提高电梯场景下检测准确度,减少误检误报警。研究结果表明:SSD检测网络对电梯内电动自行车检测效果良好,其中SSD_MobileNet网络更适用于工业领域,双摄检测方法的检测准确率均大于90%。     

Development of machine learning multi-city model for municipal solid waste generation prediction

● A database of municipal solid waste (MSW) generation in China was established. ● An accurate MSW generation prediction model (WGMod) was constructed. ● Key factors affecting MSW generation were identified. ● MSW trends generation in Beijing and Shenzhen in the near future are projected. Integrated management of municipal solid waste (MSW) is a major environmental challenge encountered by many countries. To support waste treatment/management and national macroeconomic policy development, it is essential to develop a prediction model. With this motivation, a database of MSW generation and feature variables covering 130 cities across China is constructed. Based on the database, advanced machine learning (gradient boost regression tree) algorithm is adopted to build the waste generation prediction model, i.e., WGMod. In the model development process, the main influencing factors on MSW generation are identified by weight analysis. The selected key influencing factors are annual precipitation, population density and annual mean temperature with the weights of 13%, 11% and 10%, respectively. The WGMod shows good performance with R² = 0.939. Model prediction on MSW generation in Beijing and Shenzhen indicates that waste generation in Beijing would increase gradually in the next 3–5 years, while that in Shenzhen would grow rapidly in the next 3 years. The difference between the two is predominately driven by the different trends of population growth.     

基于机器学习方法研究气象及排放变化对长三角地区主要城市大气污染物的影响

选取2015～2021年长三角地区4个代表性城市污染物浓度,利用机器学习的气象归一化方法解耦气象因素对污染物的影响,量化气象和排放对污染物浓度变化的贡献.结果表明,长三角地区PM_2.5、 NO₂和SO₂排放下降影响贡献较大(57.2%～68.2%、 80.7%～94.6%和81.6%～96.1%),抵消了气象因素带来的不利影响,致使污染物浓度降低.而气象条件对于臭氧日最大8 h(MDA8＿O₃)的贡献强于其他污染物(23.5%～42.1%),其中气象因素促进污染物浓度上升(4.7%),排放变化促进污染物浓度下降(-3.2%). NO₂和MDA8＿O₃在2019～2021年降幅更快,主要原因是2019～2021年排放起到较2015～2018年更强的促进污染物浓度降低作用.PM_2.5和SO₂在2019～2021年的降幅较2015～2021年整体有所减弱.基于机器学习的气象归一化方法可以解耦气象对污染物的影响,量化排放...     

基于机器学习利用低成本传感器数据构建城市近地面PM2.5浓度的高分辨率空间分布

PM_2.5是当前影响中国城市空气质量的一种重要污染物,它对人体健康有不利影响,高时空间分辨率的PM_2.5浓度分布是城市大气污染 精细化防控和健康影响评估的重要基础.低成本传感器在中国城市空气质量监测领域得到越来越多的应用,但由于其数据质量不够高,其价值没有得到充分的挖掘.本研究以在长三角地区蚌埠市城区作为研究案例,首先基于国控站监测数据对低成本传感器观测数据进行校准.接着通过6种机器学习模型的预测性能的比较选取随机森林作为本研究的核心方法.然后利用随机森林方法结合土地利用类型、人口密度和通过WRF模式模拟得到的气象数据、监测数据等多源数据,构建了时间分辨率为1 h、空间分辨率为0.005°（接近500 m）的近地面PM_2.5浓度的时空分布.最后对几种方法的结果进行了比较和评估.反演得到的高分辨率PM_2.5浓度的10倍交叉验证结果显示,空间R²=0.95,RMSE=9.32 μg·m^-3,时间R²=0.88,RMSE=9.24 μg·m^-3.结果表明,低成本传感器观测数据可以帮助人们构建具有更高精度的高时空分辨率的PM_2.5浓度 分布,使得低成本传感器数据的时空特征价值得到更好的利用,同时也可为低成本传感器更好地服务于空气质量精细化管理提供一种新的 应用思路.     

Machine learning and theoretical analysis release the non-linear relationship among ozone, secondary organic aerosol and volatile organic compounds

Fine particulate matter (PM_2.5) and ozone (O₃) pollutions are prevalent air quality issues in China. Volatile organic compounds (VOCs) have significant impact on the formation of O₃ and secondary organic aerosols (SOA) contributing PM_2.5. Herein, we investigated 54 VOCs, O₃ and SOA in Tianjin from June 2017 to May 2019 to explore the non-linear relationship among O₃, SOA and VOCs. The monthly patterns of VOCs and SOA concentrations were characterized by peak values during October to March and reached a minimum from April to September, but the observed O₃ was exactly the opposite. Machine learning methods resolved the importance of individual VOCs on O₃ and SOA that alkenes (mainly ethylene, propylene, and isoprene) have the highest importance to O₃ formation; alkanes (C_n, n ≥ 6) and aromatics were the main source of SOA formation. Machine learning methods revealed and emphasized the importance of photochemical consumptions of VOCs to O₃ and SOA formation. Ozone formation potential (OFP) and secondary organic aerosol formation potential (SOAFP) calculated by consumed VOCs quantitatively indicated that more than 80% of the consumed VOCs were alkenes which dominated the O₃ formation, and the importance of consumed aromatics and alkenes to SOAFP were 40.84% and 56.65%, respectively. Therein, isoprene contributed the most to OFP at 41.45% regardless of the season, while aromatics (58.27%) contributed the most to SOAFP in winter. Collectively, our findings can provide scientific evidence on policymaking for VOCs controls on seasonal scales to achieve effective reduction in both SOA and O₃.     

海洋环境耐蚀结构钢研究进展

以海洋装备主体材料钢铁作为研究对象,概述了结构钢在海洋环境下的腐蚀与防护研究进展。叙述了结构钢在海洋环境不同区域的各种因素影响下的腐蚀行为和机理。阐述了耐蚀结构钢材料的研究现状和国内外海洋环境用典型耐蚀低合金钢,目前主要通过微合金化技术和组织调控技术提高合金钢材料的耐蚀性。对比国外相关研究,我国耐蚀结构钢开发相对滞后,除了利用微合金化技术、组织调控技术这2种方法提高结构钢材料的耐蚀性外,采用传统腐蚀研究方法结合基于机器学习技术的新型腐蚀研究方法,挖掘海洋环境因素、材料成分和组织结构因素对结构钢腐蚀速率的影响规律,对加强结构钢腐蚀机理研究、加快新型耐蚀结构钢的开发、延长海洋装备的服役寿命具有重要意义。