This paper presents noise-robust clustering techniques in unsupervised machine learning. The uncertainty about the noise, consistency, and other ambiguities can become severe obstacles in data analytics. As a result, data quality, cleansing, management, and governance remain critical disciplines when working with Big Data. With this complexity, it is no longer sufficient to treat data deterministically as in a classical setting, and it becomes meaningful to account for noise distribution and its impact on data sample values. Classical clustering methods group data into "similarity classes" depending on their relative distances or similarities in the underlying space. This paper addressed this problem via the extension of classical K-means and K-medoids clustering over data distributions (rather than the raw data). This involves measuring distances among distributions using two types of measures: the optimal mass transport (also called Wasserstein distance, denoted W2) and a novel distance measure proposed in this paper, the expected value of random variable distance (denoted ED). The presented distribution-based K-means and K-medoids algorithms cluster the data distributions first and then assign each raw data to the cluster of data's distribution. These noise-robust clustering algorithms have been implemented in MatLab and applied to cluster noisy real-world weather data by efficiently extracting and using underlying uncertainty information (means and variances). The results on weather data show striking improvement in performance for W2 and ED distance-based K-means and K-medoids, and where higher accuracy is observed for ED compared to W2 for both K-means and K-medoids. This is because while W2 works with marginal distributions ignoring the actual correlations in computing the distance measure, ED works with the joint distributions factoring the correlations into the distance measurements.