산불 감지 퀴즈의 AI

퀴즈를 풀면 정답과 설명이 나타납니다.

1. What is one technical challenge for camera-based wildfire detection?
   • Distinguishing smoke from look-alikes such as fog, dust or clouds
   • Guaranteeing that every alert is a real fire
   • Determining legal liability for a utility
   • Predicting the exact path of every wildfire
2. What information does NOAA’s GOES-R Fire/Hot Spot Characterization product provide?
   • A forecast of the exact evacuation route
   • Fire location and sub-pixel characteristics such as temperature, size and radiative power
   • A guarantee that a new fire is contained
   • An automatic liability judgment for utilities
3. NOAA의 GOES와 같은 기상 위성은 어떻게 활성 화재를 감지합니까?
   • 딱딱거리는 소리를 들으면서
   • 풍속만 측정하여
   • 적외선 열이상을 감지하여
   • 나무를 세어봄으로써
4. Why can earlier wildfire detection help response teams?
   • It guarantees the fire will not spread
   • It makes satellite sensors unnecessary
   • It prevents weather from affecting fire behavior
   • It can give crews more opportunity to respond while a fire is still small
5. 시간 모델은 어떻게 탐지 신뢰도를 향상합니까?
   • 연속적인 프레임을 비교하여 표류하고 성장하는 깃털이 정적 안개로부터 돋보이게 합니다.
   • 이전 이미지를 모두 무시하여
   • 카메라 피드를 삭제하여
   • 일주일에 한 번만 보면
6. Google의 FireSat와 같은 새로운 별자리의 목적은 무엇입니까?
   • 소방관을 모두 교체하려면
   • 지구상의 거의 모든 지점을 자주 이미지화하고 매우 작은 화재를 감지하기 위해
   • 텔레비전을 방송하려면
   • 해류만 매핑하려면
7. Which satellite measurements does the GOES-R fire and hot-spot product use?
   • Only microphone recordings from ground stations
   • Radar measurements of tree height alone
   • Visible and infrared ABI spectral bands
   • Ultraviolet images of cloud tops only
8. Why do camera-based wildfire alert systems pair model output with human verification?
   • Human review is needed because cameras cannot capture images
   • Smoke models can identify the exact cause of every ignition
   • Verification makes the camera network independent of weather
   • Look-alikes such as fog, dust, and clouds can create false alerts