The USGS is conducting crop water productivity (CWP; “crop per drop”) studies of the world’s major crops (wheat, rice, corn, soybeans, barley, potatoes, pulses, sugarcane) using multiple satellite, multiple resolution remote sensing through machine learning algorithms run on cloud-computing platforms such as Google Earth Engine (GEE). The overarching goal is to understand how crops are using water for optimal productivity and where and how water can be saved through increased CWP. The methodology involves mapping crop types, modeling crop water use, modeling crop productivity, and mapping CWP. As a beginning, a meta-analysis of the global CWP was conducted. The meta-analysis established CWP of three of the world’s leading irrigated crops (wheat, corn, and rice) based on studies conducted using remote sensing data and peer-reviewed journal articles. Together, these three crops occupy 30.4% (569.3 million hectares) of the total global cropland area of 1.873 billion hectares. This study established that the United States and China are the only two countries that have consistently high CWP for wheat, corn, and rice. The quantum of water that can be saved from each crop in each country was evaluated by increasing CWP by 10, 20, and 30%. Based on data in this study, the highest consumers of water for crop production also have the most potential for water savings. These countries include the United States, India, and China for wheat; the United States, China, and Brazil for corn; and India, China, and Pakistan for rice. For example, even just a 10% increase in CWP of wheat grown in India can save 6,974 billion liters (697,400 cubic meters) of water annually, which is enough to fill 279 Olympic swimming pools. The USGS CWP webpage provides further details.