引導式測驗 · 中等 等級

水產養殖和養魚業的人工智慧測驗

了解人工智慧如何結合水下攝影機和水質感測器來監控魚類、餵食、疾病風險和農場條件。

問題 1 的 8

Which farm operations are examples of aquaculture tasks AI can support?

預覽每個問題8 問題

當您參加測驗時,就會出現答案和解釋。

  1. Which farm operations are examples of aquaculture tasks AI can support?
    • Feed management and disease or parasite monitoring
    • Predicting global seafood prices and tax rates
    • Choosing a fish species without farm or water data
    • Replacing all water-quality testing with image classification
  2. Which parasite is one example target for computer-vision monitoring in salmon farming?
    • Varroa mites
    • 海蝨
    • Downy mildew
    • Powdery mildew
  3. How can an automated feeder use camera observations to adjust pellet delivery?
    • By dispensing a fixed maximum amount regardless of fish behavior
    • By estimating each fish’s exact hunger from a single image
    • By adjusting feed delivery based on observed group feeding activity
    • By stopping all feeding whenever a camera detects motion
  4. 為什麼電腦視覺在水下尤其困難?
    • 魚的顏色太鮮豔了
    • 根本沒有光
    • 相機不能受潮
    • 能見度差、光線折射、魚群重疊移動
  5. What do stereo cameras add to fish measurement, and what is needed for weight estimates?
    • Depth supports length measurement; weight requires a calibrated relationship or model
    • They provide only color, so no size can be estimated
    • They directly weigh each fish without calibration
    • They identify salinity without a water sensor
  6. According to FAO’s SOFIA 2026 report, what share of 2024 aquatic animal production came from aquaculture?
    • 59 percent; that figure is the share of aquatic animal food output
    • 53 percent; the report compares 103 million tonnes from aquaculture with 92 million tonnes from capture fisheries
    • 75 percent of all seafood production by value
    • More than 90 percent of global aquatic animal production
  7. Which water-quality measurements did a 2021 smart-cage aquaculture study integrate?
    • Only fish body color and swimming speed
    • Wind speed, cloud cover, and rainfall only
    • Dissolved oxygen, temperature, salinity, and pH
    • Acoustic frequency, pollen color, and hive weight
  8. Which water-quality risk can a predictive model help fish-farm operators anticipate?
    • A change in the farm's software license
    • A broken camera lens without any sensor signal
    • A shift in the market price of seafood
    • A low-dissolved-oxygen event