ABSTRACT The use of earth observation data for crop mapping and monitoring in West Africa has concentrated on rainfed systems due to its pre-dominance in the sub-region. However, irrigated systems, though of limited extent, provide critical livelihood support to many. Accurate statistics on irrigated crops are, thus, needed for effective management and decision making. This study explored the use of Sentinel 1 (S-1) and Sentinel 2 (S-2) data to map the extent and yield of irrigated crops in an informal irrigation scheme in Burkina Faso. Random Forest classification and regression were used together with an extensive field data comprising 842 polygons. Four irrigated crops (tomoto, onion, green bean and other) were classified while the yield of tomatoes was modelled through regression analysis. Apart from spectral bands, derivatives (e.g. biophysical parameters and vegetation indices) from S-2 were used. Different data configuration of S-1, S-2 and their derivatives were tested to ascertain optimal temporal windows for accurate irrigated crop mapping and yield estimation. Results of the crop classification revealed a greater overall accuracy (76.3%) for S-2 compared to S-1 (69.4%), with S-2 biophysical parameters (especially the fraction of absorbed photosynthetic active radiation i.e fAPAR) being prominent. For yield prediction, however, S-1 VV polarization came up as the most prominent predictor in the regression analysis ( = 0.63), while the addition of S-2 fAPAR marginally improved the fit ( = 0.64). Tomato yield in the study area was found to range from 1 to 16 kg m−2, although about 83% of the area have yields of less than 10 kg m−2. Our study revealed that early season images (acquired in December) perform better in classifying irrigated crop compared to mid or late season. On the other hand, the use of early to mid-season (December to February) images for yield modelling produced reasonable prediction accuracy. This indicates the possibility of using S-1 and S-2 data to predict crop yield prior to harvest season for efficient planning and food security attainment.

中文翻译：

---

在半干旱小农灌溉计划中使用定点产品进行作物监测和产量估算

摘要 由于雨育系统在该次区域的主导地位，在西非使用地球观测数据进行作物测绘和监测的重点是雨养系统。然而，灌溉系统虽然范围有限，但为许多人提供了重要的生计支持。因此，有效管理和决策需要有关灌溉作物的准确统计数据。本研究探讨了如何使用哨兵 1 (S-1) 和哨兵 2 (S-2) 数据绘制布基纳法索非正式灌溉计划中灌溉作物的范围和产量。随机森林分类和回归与包含 842 个多边形的广泛现场数据一起使用。对四种灌溉作物（番茄、洋葱、绿豆等）进行分类，同时通过回归分析对西红柿的产量进行建模。除了光谱带，衍生物（例如 使用来自 S-2 的生物物理参数和植被指数。测试了 S-1、S-2 及其衍生物的不同数据配置，以确定用于准确灌溉作物绘图和产量估算的最佳时间窗口。作物分类结果显示，与 S-1 (69.4%) 相比，S-2 的总体准确度 (76.3%) 更高，其中 S-2 生物物理参数（尤其是吸收的光合有效辐射的分数，即 fAPAR）尤为突出。然而，对于产量预测，S-1 VV 极化是回归分析中最突出的预测因子 (= 0.63)，而添加 S-2 fAPAR 略微改善了拟合 (= 0.64)。发现研究区域的番茄产量范围为 1 至 16 kg m-2，尽管约 83% 的区域的产量低于 10 kg m-2。我们的研究表明，与中季或晚季相比，早季图像（在 12 月获得）在对灌溉作物进行分类方面表现更好。另一方面，使用早到中期（12 月至 2 月）图像进行产量建模产生了合理的预测准确性。这表明可以使用 S-1 和 S-2 数据在收获季节之前预测作物产量，以实现高效规划和实现粮食安全。