Tectonic fragmentation of continents is commonly accommodated by continental-scale networks of rift basins and microplates along evolving divergent plate boundaries. Yet, little is known of the geometrical controls of the microplate initiation. We explore the East African Western Rift, where the Nubian-Victoria plate boundary is collocated with a ~200-km wide region of seismicity, low wave speed lithosphere, and hot springs that extend outboard of the previously proposed active rift axis and westward into the Congo Craton, across the poly-deformed intersection zone of Paleoproterozoic NW-trending Ruzizian-Ubendianand Mesoproterozoic NE-trending Kibaran orogenic belts. To unravel the mechanisms by which the continental lithosphere is accommodating the regional tectonic strain, we explore a network of two contiguous poorly-studied rift basins in eastern DRC: the NW-striking Luama Rift, commonly characterized as a ’failed’ Mesozoic rift, and its adjacent NE-striking Kamituga Rift located craton-ward. In the two rift basins, we unveil and analyze previously unknown widespread systems of 2 - 170-km long active faults with 10 - 130-m high scarps, and resolve their contemporary stress states, and length-scale attributes. The results reveal: 1) failure-optimal orientation of faults in the contemporary EARS stress field, 2) power-law fault-length distribution in the border-faulted Luama Rift compatible with rejuvenation of a failed rift, and ’conditional’ power-law distribution in the Kamituga Rift, compatible with incipient extension along a southwestward continuation of the Kivu Rift, and 3) a previously unknown microplate, the Itombwe Microplate. We propose that the seemingly broad active deformation along the Western rift is accommodated by a nucleating microplate and incipient rifts.

Improving the accuracy of streamflow predictions in ungauged basins (PUB) has long been a significant challenge in hydrological research. This study hypothesizes that deep learning-based PUB can be enhanced for historical streamflow reconstruction by integrating local climate data from ungauged or partially gauged basins (the target site) with streamflow measurements from nearby gauged basins (donor sites). The rationale is that streamflow records from donor sites offer valuable information for predicting streamflow at the target site. However, in some instances, local weather data may be more readily available, while available donors might be poorly correlated with the target. Therefore, prediction accuracy can be improved by weighting both sources effectively. To test this hypothesis, we conducted a case study using over 200 streamflow gauges in the Great Lakes region. We developed a multi-layer perceptron to estimate Spearman rank correlations of streamflow between basins, aiding in the selection of donor sites. These estimated correlations were fed into a Long Short-Term Memory (LSTM) network, along with streamflow data from donor sites and weather data from target sites. We compared this model against two other LSTMs, one trained only on climate data and the other solely on streamflow data from donor sites, as well as the average prediction from those two models. Our findings indicate that the integrated approach outperforms the alternatives, particularly for partially gauged sites and natural ungauged sites. Lastly, we demonstrate the value of the approach for improving lake-wide runoff estimates and underscore its implications for quantifying the Great Lakes water balance.