Monitoring | PANORAMA

AI-based crack gauge for rockfall

AI-based crack guage

KNPS

AI-based crack gauge

TV chosun

AI-based crack gauge for rockfall is a device that monitors the occurrence of rockfall and the crack displacements in real-time by installing an observation sensor in a rockfall risky area located along the trail. Since 2013, automatic and manual crack gauges have been installed on steep slopes with a high risk of collapse, and 525 units are currently in operation at 174 locations. The rockfall measuring device is divided into risk levels of 'interest, caution, alert, and serious'. In the interest stage, regular and frequent inspections are carried out. In the caution stage where cracks are less than 5 mm and less than 2°, monitoring is strengthened. In the alert stages, precise investigation and action plans for the disaster are prepared. In the serious stage, the adjacent trails are controlled and emergency measures such as rockfall removal are implemented.

Prior to the installation of the AI-based crack gauge, a dedicated investigation team composed of geologists and disaster prevention experts was established in advance to systematically manage rockfalls and steep slopes to investigate areas with risk of rockfall accidents along the trails of national parks. In addition, the safety hazardous areas were graded from A to E according to the degree of risk, steepness, and other geologic characteristics and converted into databases.

81 rockfall events have occurred in the national park during the last 10 years, resulting in 3 deaths and 6 injuries, damaging properties of about KRW 2.1 billion. However, since 2018, when the AI-based crack gauge was used, there has been no fatality or injury to visitors due to rockfalls. In addition, it took a lot of time and labor to inspect all the crack gauges installed throughout the national park one by one. With the saved time park rangers can concentrate more on park other management activities, which greatly improved the internal satisfaction.

Implementation

Monitoring

National

AI-based crack gauge of KNPS

AI-based intelligent CCTV

AI-based intelligent CCTV of KNPS

KNPS

AI-based intelligent CCTV of KNPS

KNPS

AI-based Intelligent CCTV is a scientific safety management system that uses deep learning technology to control emergencies in real-time image analysis. By recognizing and analyzing abnormal behavior patterns, such as intrusion, screaming, wandering, etc., a warning broadcast is immediately sent to the site and delivered to the control system, following the emergency responses.
In addition, in the case of marine/coastal national parks with a high risk of safety accidents due to tides and tides, the broadcast of tide times is automatically issued to the site. Intelligent CCTV was installed in 2020 and is currently being operated in 89 places in 15 national parks.

The most important enabling factor is to select the optimal location where the equipment can be operated effectively. Intelligent CCTV was installed by selecting areas where drowning accidents occurred frequently in the past. Another success factor is having a set of systems to deal with emergencies. When the AI alarm system is activated, the general control center in KNPS HQ checks real-time streaming to quickly grasp the situation and then rescue teams in national parks on the spot to start rescue operations.

AI-based intelligent CCTV is a scientific safety management system using deep learning technology. In order to continuously improve the accuracy of deep learning, experts continue to maintain the software and provide technical support in the field so that it can be managed stably. As data for deep learning is accumulating, it is expected that the operating level of the system will be increased. Based on these achievements and limitations, it is necessary to improve the numerous CCTVs that have been monitored by manpower using this innovative technology gradually in connection with the KNPS safety management system.

Implementation

Monitoring

National

AI-based intelligent CCTV of KNPS 1

AI-based intelligent CCTV of KNPS 2

AI-based intelligent CCTV of KNPS 3

Biodiversity Impact Assessment Tool (BiA)

BiA Tool Method: overlaying geographic layers

Shan Shui Conservation Center

BiA Tool: Home page

Shan Shui Conservation Center

BiA Tool: Search page

Shan Shui Conservation Center

BiA Tool: Enquiry result

Shan Shui Conservation Center

To enable automatic and instant biodiversity impact assessment enquiry, the BiA tool has been developed to facilitate enquiry services for land planners and other interested parties via Azure platform. The BiA tool works by overlaying the enquiry site or region (or existing construction projects) with multiple geographic layers including species distribution and protected area range to investigate if the site or region is within certain distance (e.g., 3 km, 5 km) from and may cause impact on endangered species habitat and/or protected areas. The assessment reports illustrate ecological and environmental risks of construction projects for decision-makers and could hopefully promotes them to take biodiversity into consideration.

A brief timeline of the BiA tool:

Apr-Jun 2020: team formation, requirement communication, system development plan
Jul-Sept 2020: tool development
Oct 2020: trial test, application and dissemination
(in preparation) Apr-Sept 2022: system upgrade

Years of data collection accumulation and constant thinking of data application approaches.
Theoretical & technical basis accumulated from long-term research and conservation practice.
Promotion of the BiA tool to its potential users, like governments, investors, and enterprise.
Keeping track of tool operation and user feedback to devise further upgrade of the tool.

Data application is the foremost step in the whole data workflow, where the data turns into valuable information for stakeholders. Effective data application reports should bear the audience in mind (e.g., being concise and focused).
The complete of development and releasing is not the last step for a tool. Finding potential users and persuading them to use the tool is also very important. A tool has to be used to provide the most value.

Documentation and dissemination of results

Biodiversity Impact Assessment Tool Handbook_CN

Sample BiA Report

Biodiversity Impact Assessment Tool

Citizen science data visualization platform

Spatial campaign page displaying squirrel investigation results

Shan Shui Conservation Center

Spatial and temporal campaign page displaying gingko investigation results

Shan Shui Conservation Center

Species records in Yunnan province

Shan Shui Conservation Center

[GIF] Home page and spatial campaign page (e.g., squirrel investigation results)

Shan Shui Conservation Center

[GIF] Spatial and temporal campaign page (e.g., gingko investigation results)

Shan Shui Conservation Center

[GIF] Data visualization on different administrative division levels (e.g., Zhejiang Province)

Shan Shui Conservation Center

During nature watch campaigns, citizen scientists are invited to observe and record wildlife timely, which not only strengthens the connection between citizens and nature but also serves as a promising species distribution data source. Species record data collected by citizen scientists via online questionnaire automatically flows into the visualization platform database (after data cleaning and manually periodically check) and turns into intuitive and attractive visualized charts and maps (two types: spatial, spatial and temporal) via Power BI. The platform, with both web and mobile version, provides real-time feedback to citizen scientists’ nature watch efforts, boosting their sense of accomplishment and motivating their future participation in nature watch activities. Moreover, since the platform integrates multiple nature watch campaigns with links to web articles about specific analysis of each campaign, it offers a broad range of biodiversity knowledge and enables “virtual nature watch” for citizens to get to know wildlife in other regions.

A brief timeline of the platform:

Jan-Feb 2021: form team, analyze analysis, make blueprint
Mar-Jun 2021: develop database and platform
Jul-Aug 2021: trial test
Sept 2021: go live and promotion

A well-designed data-collection questionnaire and automatic data cleaning mechanism to ensure data quality and a manually periodically check (normally once a season) to ensure data reality.
Visualization methods selection and aesthetic design with the engagement of citizen scientists.
PowerBI technology.
Citizen scientist WeChat community operation and maintenance.

As a public outreach product, it would never be too much for polishing contents and aesthetic design to make the platform user-friendly and attractive.
Engaging users in the planning stage and collecting their thoughts is very helpful for identifying user needs.
Questionnaires are needed to be well-designed and citizen scientists are needed to be well-trained before recording data. Otherwise, it’s easy to cause data loss.

Implementation

Monitoring

Documentation and dissemination of results

Local

Subnational

Citizen science data visualization platform introduction

Citizen science data visualization platform web version

Camera trap data management system

AI detected camera trap image: red fox in the Sanjiangyuan region

Shan Shui Conservation Center

AI detected camera trap image: snow leopard in the Sanjiangyuan region

Shan Shui Conservation Center

Community-based camera trap monitoring assistant app

Shan Shui Conservation Center

Camera trap data management system: species identification page

Shan Shui Conservation Center

To accelerate camera trap data workflows, an online data management system along with app-based tools and AI image recognition is being developed supported by technical partners, which consists of:

Community-based camera trap monitoring assistant app: the app allows local monitors to automatically record the time and GPS location of camera trap setup/pickup, saving the cumbersome process of collecting data from local monitors and manual data entry. (blueprint: Jun 2019, development: Oct 2019-Feb 2020, trial and use: Mar-Oct 2020)
AI image recognition models: AI models help detect animals and identify species in camera trap photos, which greatly reduce the number of photos that need human identification and enhance data processing efficiency.
- A series of AI models has been trained and/or tested with technical partners, including PU & PKU ResNet18 model (2018), MegaDetector (test only, 2020), MindSpore YOLOv3 model (2021).
Online data management platform: camera trap information collected via the app along with photos are upload to a structured cloud database. The data management platform not only supports species identification via AI and human, but also enables global data search and statistics reports. (blueprint: Apr-Aug 2021, development: Sept 2021-Jun 2022, trial and use: Jul 2022)

A systematic review of the current camera trap data workflow and translating into technical system development needs
Open-source and good-performing camera trap image AI recognition models
Cloud resources for AI computing, data storage, etc.
Rounds of trial use and feedback to fix bugs and improve the usability of the system

Rome was not built in a day. Due to time and resource constraints, we have to divide the system into different modules and develop modules step by step. We believe that each module itself can enhance one or more steps in our workflow and have benefited from modules before they are incorporated into the full system. Yet it is important to have a big-picture perspective in the beginning and make long-term plans for the final system integration.
A system cannot be perfect from the start. When the app first came out and put into use in one community, it did not work as we expected and local monitors reported various types of bugs. We collected and analyzed the feedbacks to improve the UI-design and functionality of the app.

Training and Capacity Building

Training staff in the use of digital mobile data collection.

map scientific services

Training of staff is important to ensure the effective implementation and long-term success of the solution. Prioritise training during the designing and deployment phase, as well as after the deployment to ensure continued use of the solution.

Technical officers or champions to drive the training and use on the ground improve the chance of success.

Use the organisational reporting tools to track user engagement and usage to pinpoint when and if they are not using the applications as planned. Identify why there may be a problem, and work with them to overcome the problem.
Language barriers can be an issue and forms need to be simple for effective data collection.
Training should not be seen as a once-off exercise but rather a continuous process.
Staff turnover is a reality and organisations need to ensure continuity by always having more than one senior staff member trained on the various workflows and administration of ArcGIS Online.
Implementation partners can make training and long-term support of the solution more manageable.

Implementation

Monitoring

Local

Restor Platform

Huaravito Reserve on Restor

Randall Santamaria - Huaravito Reserve

Thanks to the Restor.eco platform, we analyze the restoration potential of our reserve, monitoring changes over time with satellite images and geospatial data, thus knowing the local biodiversity and its characteristics, current and potential soil carbon, as well as other variables such as patterns of land cover, soil acidity, or annual precipitation, using machine learning, artificial intelligence, and scientific units of measure.

Access to spatial information.
Updated scientific data and resources.
Increases the impact, scale, and sustainability of restoration efforts.

Restor is accelerating the global restoration movement by connecting everyone, everywhere to local restoration.
Restor connects people to scientific data, supply chains, funding, and each other to increase the impact, scale, and sustainability of restoration efforts.
Is not just about trees or forests, but also about grasslands, wetlands, coastal habitats and all the other places that support life on Earth.

Monitoring

Documentation and dissemination of results

Local

Global

Huaravito Reserve on Restor

Mobile Apps

Environmental Education

Randall Santamaria - Huaravito Reserve

The use of mobile Apps such as eBird, iNaturalist, Merlin Bird ID, provocated a positive impact for us on monitoring ecosystem and biodiversity.

Community engagement and environmental education.
Support of international organizations such as Cornell Lab of Ornithology and Environment for the Americas.

Local knowledge and local communities are very important for monitoring process and ecosystem conservation/restoration.

Monitoring

Documentation and dissemination of results

Local

Huaravito Reserve on iNaturalist

Population Monitoring

Marking and Measuring

Raymond A Saumure

Agency-lead mark-recapture sessions were conducted to assess population status. Population status (i.e., whether the population is stable, increasing, or decreasing) is an important biological indicator of project success. If fish numbers are decreasing, adaptive management strategies can be enacted and try to reverse trends. Conversely, if they are increasing the success can be replicated at other sites.

Mark-recapture sessions are lead by the Nevada Department of Wildlife with assistance from the US Fish and Wildlife Servive, Springs Preserve and Southern Nevada Water Authority staff. Such cooperation leads to better communication and continued project support.

Following a fall mark-recapture session in October of the first year of the project, live fish were collected with a layer of fungus growing over their bodies. A USFWS fish pathology laboratory concluded that “immunosuppressed mature fish were succumbing to opportunistic aquatic bacteria and fungi.” Pathologists speculated that the pathogens were the result of two confounding stressors: (1) environmental – a 7°C degree drop in water temperature (i.e., from 22°C to 15°C between the 1st and 2nd capture sessions); and (2) anthropogenic – trapping, handling, and marking during a mark-recapture survey. Consequently, the timing of mark-recapture surveys was moved from fall to late summer and the issue has not reoccurred since.

Monitoring

Local

Coordination Platform for Sustainable Pasture Management

A Pasture Coordination Platform was organized in Armenia as a horizontal management network among relevant stakeholders on national and sub-national level. Each party is represented by a spokesperson, who coordinates the functions of the party within the Platform and ensures information flow. A secretariat ensures the operation of the Platform. The rationale for creation of the Platform was the need to promote effective cooperation, exchange of information, as well as coordination of activities among the projects implemented in Armenia, focusing on sustainable management of natural fodder areas.

Since 2018 the Platform has evolved and now more than 10 organizations, institutions, projects and public administration bodies are involved in the Platform’s activities, aiming to ensure viability of programs and investments in the area of animal farming, increase economic opportunities of communities and support income growth of rural residents in Armenia. Key objectives of the Coordination Platform are:

Coordination, exchange of information exchange and experience, identification of potential cooperation areas
Implementation of joint projects, activities
Advocating and supporting development of relevant state policy and legislation promoting sustainable use and management of natural fodder areas

The platform has a clear aim: "to improve the situation/ livelihood of the rural population which depends on natural fodder areas while sustainably using and conserving these natural ecosystems”.
The need for coordination, cooperation and exchange was felt by parties both from government as well as non-government organizations.
A memorandum was officially signed to establish the platform.
All members have clearly distinguished functions.

Active participation of the community stakeholders in decision making and coordination of the local projects was crucial. Placing the local working groups in charge of the local implementation not only generated a high level of ownership of the project and ensured the engagement of the community.

The coordination with other development organizations on the local scale was a key factor. The harmonization of these different local interventions resulted in a comprehensive, positive change for the communities. Each intervention was complimented by the others and would not have achieved the same results as an isolated activity.

Based on the memorandum of understanding, the common interest and need of all stakeholders in the platform to cooperate increased their commitment and ensured the continuity of the process.

Multi stakeholder advisory bodies face high risks from unforeseen changes in governmental institutions or even within their own parties. The meticulous documentation of agreements and activities has proven to be an important measure for dealing with this risk.

Implementation

Monitoring

Documentation and dissemination of results