Detection and prediction of land use change impact on stream flow regime in Sahelian river basin, northwestern Nigeria

Detecting and predicting the impact of land use/land cover (LULC) changes on streamflow are crucial sources of information for the effective management and protection of land and water resources in Sahelian ecosystems such as the Hadejia river basin. In this study, LULC change detection was performed using ENVI, while the LULC modeling was conducted using the cellular automata (CA)–Markov in the IDRISI environment. However, the streamflow trend and variation were assessed using the Mann–Kendall (MK) trend test and the inverse distance weightage (IDW). Before the LULC modeling and projection (2030), the LULC was classified for 1990, 2000, and 2010 using supervise classification. Model output revealed a strong relationship between LULC and streamflow trend, thus, the decade 1990–2000, was the decade with high forest clearance and streamflow output, consequently severe floods. However, the decade 2000–2010 witnessed land use expansion mainly via construction (3.4%). Meanwhile, the scenario will slightly change in the future as agriculture is projected to expand by about 9.3% from 2010 to 2030 due to the increased human population. Thus, food insecurity aggravated by climate change should be anticipated, and measures to avert/reduce their effects must be initiated.

Semi-Supervised Point Prototype Clustering

This paper describes a class of models we call semi-supervised clustering. Algorithms in this category are clustering methods that use information possessed by labeled training data Xd⊂ ℜp as well as structural information that resides in the unlabeled data Xu⊂ ℜp. The labels are used in conjunction with the unlabeled data to help clustering algorithms partition Xu ⊂ ℜp which then terminate without the capability to label other points in ℜp. This is very different from supervised learning, wherein the training data subsequently endow a classifier with the ability to label every point in ℜp. The methodology is applicable in domains such as image segmentation, where users may have a small set of labeled data, and can use it to semi-supervise classification of the remaining pixels in a single image. The model can be used with many different point prototype clustering algorithms. We illustrate how to attach it to a particular algorithm (fuzzy c-means). Then we give two numerical examples to show that it overcomes the failure of many point prototype clustering schemes when confronted with data that possess overlapping and/or non uniformly distributed clusters. Finally, the new method compares favorably to the fully supervised k nearest neighbor rule when applied to the Iris data.