公告：凡是在
2025 年 4 月 15 日前註冊使用 Earth Engine 的非商業專案，都必須
驗證非商業用途資格，才能繼續存取 Earth Engine。
ee.Algorithms.TemporalSegmentation.Verdet
透過集合功能整理內容
你可以依據偏好儲存及分類內容。
透過森林變化偵測演算法，估算一段時間內的植被再生和干擾情況。這項演算法會根據衛星影像生成年度晴空複合影像，計算該複合影像中每個像素的光譜植被指數，將植被指數影像空間分割成圖塊，將時間序列劃分為不同斜率的區段，然後將這些區段標示為受干擾、穩定或再生。空間和時間步驟的區隔作業都會使用全變差正規化。
輸出結果為每個像素的 1D 陣列，內含已調整趨勢線的斜率。負值表示干擾，正值表示再生。
請參閱：Hughes, M.J.，Kaylor, S.D. 和 Hayes, D.J.，2017 年。 根據 Landsat 時間序列資料，以修補程式為基礎偵測森林變化。Forests, 8(5), p.166.
| 用量 | 傳回 |
|---|
ee.Algorithms.TemporalSegmentation.Verdet(timeSeries, tolerance, alpha, nRuns) | 圖片 |
| 引數 | 類型 | 詳細資料 |
|---|
timeSeries | ImageCollection | 要從中擷取 VeRDET 分數的集合。這個集合預計會包含每年 1 張圖片，並依時間排序。 |
tolerance | 浮點值，預設值為 0.0001 | 收斂容許值。 |
alpha | 浮點值，預設值：0.03333333333333333 | 用於區隔的正則化參數。 |
nRuns | 整數，預設值為 100 | 收斂的執行次數上限。 |
除非另有註明，否則本頁面中的內容是採用創用 CC 姓名標示 4.0 授權，程式碼範例則為阿帕契 2.0 授權。詳情請參閱《Google Developers 網站政策》。Java 是 Oracle 和/或其關聯企業的註冊商標。
上次更新時間：2025-07-26 (世界標準時間)。
[null,null,["上次更新時間：2025-07-26 (世界標準時間)。"],[[["\u003cp\u003eThe algorithm detects forest change by analyzing yearly satellite imagery and identifying areas of disturbance and regeneration.\u003c/p\u003e\n"],["\u003cp\u003eIt uses a spectral vegetation index and segments the imagery spatially and temporally to track vegetation changes.\u003c/p\u003e\n"],["\u003cp\u003eDisturbance is indicated by negative trend slopes, while regeneration is indicated by positive slopes in the output array.\u003c/p\u003e\n"],["\u003cp\u003eThe algorithm utilizes total variation regularization for both spatial and temporal segmentation to enhance accuracy.\u003c/p\u003e\n"],["\u003cp\u003eUsers can adjust parameters like tolerance, regularization, and maximum runs for customized analysis using the provided function.\u003c/p\u003e\n"]]],[],null,["# ee.Algorithms.TemporalSegmentation.Verdet\n\nVegetation Regeneration and Disturbance Estimates through Time, forest change detection algorithm. This algorithm generates a yearly clear-sky composite from satellite imagery, calculates a spectral vegetation index for each pixel in that composite, spatially segments the vegetation index image into patches, temporally divides the time series into differently sloped segments, and then labels those segments as disturbed, stable, or regenerating. Segmentation at both the spatial and temporal steps are performed using total variation regularization.\n\n\u003cbr /\u003e\n\nThe output consists of a 1D array per pixel containing the slope of fitted trend lines. Negative values indicate disturbance and positive values regeneration.\n\nSee: Hughes, M.J., Kaylor, S.D. and Hayes, D.J., 2017. Patch-based forest change detection from Landsat time series. Forests, 8(5), p.166.\n\n| Usage | Returns |\n|------------------------------------------------------------------------------------------------|---------|\n| `ee.Algorithms.TemporalSegmentation.Verdet(timeSeries, `*tolerance* `, `*alpha* `, `*nRuns*`)` | Image |\n\n| Argument | Type | Details |\n|--------------|-------------------------------------|----------------------------------------------------------------------------------------------------------------------------------|\n| `timeSeries` | ImageCollection | Collection from which to extract VeRDET scores. This collection is expected to contain 1 image for each year, sorted temporally. |\n| `tolerance` | Float, default: 0.0001 | Convergence tolerance. |\n| `alpha` | Float, default: 0.03333333333333333 | Regularization parameter for segmentation. |\n| `nRuns` | Integer, default: 100 | Maximum number of runs for convergence. |"]]
