Abstract High spatio-temporal variability of daily rainfall in Bali Island can create the absence of structure in the daily variogram in certain days. This research proposes a new technique applying space–time variogram for 3-successive daily rainfall to detect structure in variogram estimation by merging rain gauges and satellite data applying ordinary kriging (OK), regression kriging with CMORPH (CM), regression kriging with TRMM (TR), and blended monthly rainfall (MONT) to obtain daily blended gridded rainfall estimates. Original retrieval of CMORPH (CM_OR) and TRMM (TR_OR) also used as control points to assess the proposed method. Uncertainty and sensitivity analysis including cross validation were carried out to validate the proposed method. The result shows that a new technique, adapted from CMORPH specific character, can be applied to detect the existence of structure in variogram. Blended gridded daily rainfall estimates of CM has highest probability detection of rainy events, while OK the lowest. Generally, the four interpolation methods (OK, CM, MONT, TR) have low accuracy at leeward and in a coastal area. All of them have almost similar performance indicated by no clear distinction of RMSE value from cross validation. CM, MONT, and TR have a good sensitivity with maximum and minimum temperature, indicating that satellite data can improve the gridded rainfall estimates. However, it is required an improvement of daily gridded rainfall estimates since there are large RMSE values and low coefficient correlation in certain days because of strong and erratic behavior of rainy events in a mountainous tropical island of Bali.

中文翻译：

---

使用雨量计和卫星数据估算印度尼西亚巴厘岛热带山区岛屿日降雨量的时空变异函数（初步研究）

摘要 巴厘岛日降雨量的高时空变异性会导致某些日子的日变异函数缺乏结构。本研究提出了一种新技术，将时空变异函数应用于 3 次连续日降雨量，通过合并雨量计和卫星数据应用普通克里金法 (OK)、回归克里金法与 CMORPH (CM)、回归克里金法与 TRMM 来检测变异函数估计中的结构。 TR) 和混合月降雨量 (MONT) 以获得每日混合网格降雨量估计值。CMORPH (CM_OR) 和 TRMM (TR_OR) 的原始检索也用作控制点来评估所提出的方法。进行了包括交叉验证在内的不确定性和敏感性分析以验证所提出的方法。结果表明，一种改编自 CMORPH 特定特征的新技术，可用于检测变异函数中结构的存在。CM 的混合网格日降雨估计具有最高的降雨事件检测概率，而 OK 最低。通常，四种插值方法（OK、CM、MONT、TR）在背风和沿海地区精度较低。所有这些都具有几乎相似的性能，这表明 RMSE 值与交叉验证没有明显区别。CM、MONT 和TR 对最高和最低温度具有良好的敏感性，表明卫星数据可以改进网格化降雨估计。然而，需要改进每日网格降雨量估计值，因为在巴厘岛山区热带岛屿降雨事件的强烈和不稳定行为，在某些日子里存在较大的 RMSE 值和低系数相关性。