Improved Use of Drone Imagery for Malaria Vector Control through Technology-Assisted Digitizing (TAD)

Drones have the potential to revolutionize malaria vector control initiatives through rapid and accurate mapping of potential malarial mosquito larval habitats to help direct field Larval Source Management (LSM) efforts. However, there are no clear recommendations on how these habitats can be extracted from drone imagery in an operational context. This paper compares the results of two mapping approaches: supervised image classification using machine learning and Technology-Assisted Digitising (TAD) mapping that employs a new region growing tool suitable for non-experts. These approaches were applied concurrently to drone imagery acquired at seven sites in Zanzibar, United Republic of Tanzania. Whilst the two approaches were similar in processing time, the TAD approach significantly outperformed the supervised classification approach at all sites (t = 5.1, p < 0.01). Overall accuracy scores (mean overall accuracy 62%) suggest that a supervised classification approach is unsuitable for mapping potential malarial mosquito larval habitats in Zanzibar, whereas the TAD approach offers a simple and accurate (mean overall accuracy 96%) means of mapping these complex features. We recommend that this approach be used alongside targeted ground-based surveying (i.e., in areas inappropriate for drone surveying) for generating precise and accurate spatial intelligence to support operational LSM programmes.

Deep Semi-Supervised Image Classification Algorithms: a Survey

Semi-supervised learning is a branch of machine learning focused on improving the performance of models when the labeled data is scarce, but there is access to large number of unlabeled examples. Over the past five years there has been a remarkable progress in designing algorithms which are able to get reasonable image classification accuracy having access to the labels for only 0.1% of the samples. In this survey, we describe most of the recently proposed deep semi-supervised learning algorithms for image classification and identify the main trends of research in the field. Next, we compare several components of the algorithms, discuss the challenges of reproducing the results in this area, and highlight recently proposed applications of the methods originally developed for semi-supervised learning.

Analysis of Vegetative Cover Vulnerability in Rohingya Refugee Camps of Bangladesh Utilizing Landsat and Per Capita Greening Area (PCGA) Datasets

The vegetative cover in and surrounding the Rohingya refugee camps in Ukhiya-Teknaf is highly vulnerable since millions of refugees moved into the area, which led to severe environmental degradation. In this research, we used a supervised image classification technique to quantify the vegetative cover changes both in Ukhiya-Teknaf and thirty-four refugee camps in three time-steps: one pre-refugee crisis (January 2017), and two post-refugee crisis (March 2018, and February 2019), in order to identify the factors behind the decline in vegetative cover. The vegetative cover vulnerability of the thirty-four refugee camps was assessed using the Per Capita Greening Area (PCGA) datasets and K-means classification techniques. The satellite-based monitoring result affirms a massive loss of vegetative cover, approximately 5482.2 hectares (14%), in Ukhiya-Teknaf and 1502.56 hectares (79.57%) among the thirty-four refugee camps, between 2017 and 2019. K-means classification revealed that the vegetative cover in about 82% of the refugee camps is highly vulnerable. In the end, a recommendation as to establishing the studied region as an ecological park is proposed and some guidelines discussed. This could protect and reserve forests from further deforestation in the area, and foster future discussion among policymakers and researchers.

SATELLITE IMAGERY DRIVEN ASSESSMENT OF LAND USE LAND COVER, URBANIZATION AND SURFACE TEMPERATURE PATTERN DYNAMICS OVER TROPICAL MEGACITIES

In most of the developing nations, fast paced urbanisation is going on. This has changed the spatial patterns of Land Use Land Cover (LULC) and Land Surface Temperature (LST) over time. Continual studies are required in this context to know these phenomena more clearly. This study is carried out to analyse the spatio-temporal changes in LULC, urbanisation and LST in the metropolitan cities of India namely Delhi and Bengaluru. Landsat images of TM and OLI sensors are taken for the years 2001, 2010 and 2020. The LULC layer is obtained through supervised image classification. Concentric circles at the interval of 2 km are drawn from the centroid of the study areas which are used to compute Shannon's entropy through zonal analysis of the reclassified LULC layer. The thermal band of the Landsat is used for the computation of LST. The results of both the study areas revealed 1) decline in the open land, vegetation and water body; 2) rampant growth of built-up and urban area which become more compact over the years; and 3) spread of the higher LST zones.

Land Use and Land Cover Change Detection Using Remote Geospatial Techniques: A Case Study of an Urban City in Southwestern, Nigeria

Many cities in developing countries are experiencing ecosystem modification and change. Today, about 10 million hectares of the world’s forest cover have been converted to other land uses. In Nigeria, there is an estimated increase of 8.75 million ha of cropland and decrease of about 1.71 million ha of forest cover between 1995 to 2020, indicating that Nigeria has been undergoing a wide range of land use and land cover changes. This paper analyses the changes in land use/cover in Ila Orangun, Southwestern, Nigeria from 1986 to 2018, with a view to providing adequate information on the pattern and trend of land use and land cover changes for proper monitoring and effective planning. The study utilized satellite images from Landsat 1986, 2002 and 2018. Remote sensing and Geographical Information System techniques as well as supervised image classification method were used to assess the magnitude of changes in the city over the study period. The results show that 26.36% of forest cover and 44.48% of waterbody were lost between the period of 1986 and 2018. There was a rapid increase in crop land by 365.7% and gradual increase in built-up areas by 103.85% at an annual rate of 3.25%. Forest was the only land cover type that recorded a constant reduction in areal extent. The study concluded that the changes in land use and land cover is a result of anthropogenic activities in the study area.

Image-Based Insider Threat Detection via Geometric Transformation

Insider threat detection has been a challenging task over decades; existing approaches generally employ the traditional generative unsupervised learning methods to produce normal user behavior model and detect significant deviations as anomalies. However, such approaches are insufficient in precision and computational complexity. In this paper, we propose a novel insider threat detection method, Image-based Insider Threat Detector via Geometric Transformation (IGT), which converts the unsupervised anomaly detection into supervised image classification task, and therefore the performance can be boosted via computer vision techniques. To illustrate, our IGT uses a novel image-based feature representation of user behavior by transforming audit logs into grayscale images. By applying multiple geometric transformations on these behavior grayscale images, IGT constructs a self-labelled dataset and then trains a behavior classifier to detect anomaly in a self-supervised manner. The motivation behind our proposed method is that images converted from normal behavior data may contain unique latent features which remain unchanged after geometric transformation, while malicious ones cannot. Experimental results on CERT dataset show that IGT outperforms the classical autoencoder-based unsupervised insider threat detection approaches, and improves the instance and user based Area under the Receiver Operating Characteristic Curve (AUROC) by 4% and 2%, respectively.

A Synthesis of Spatial Forest Assessment Studies Using Remote Sensing Data and Techniques in Pakistan

This paper synthesizes research studies on spatial forest assessment and mapping using remote sensing data and techniques in Pakistan. The synthesis states that 73 peer-reviewed research articles were published in the past 28 years (1993–2021). Out of all studies, three were conducted in Azad Jammu & Kashmir, one in Balochistan, three in Gilgit-Baltistan, twelve in Islamabad Capital Territory, thirty-one in Khyber Pakhtunkhwa, six in Punjab, ten in Sindh, and the remaining seven studies were conducted on national/regional scales. This review discusses the remote sensing classification methods, algorithms, published papers' citations, limitations, and challenges of forest mapping in Pakistan. The literature review suggested that the supervised image classification method and maximum likelihood classifier were among the most frequently used image classification and classification algorithms. The review also compared studies before and after the 18th constitutional amendment in Pakistan. Very few studies were conducted before this constitutional amendment, while a steep increase was observed afterward. The image classification accuracies of published papers were also assessed on local, regional, and national scales. The spatial forest assessment and mapping in Pakistan were evaluated only once using active remote sensing data (i.e., SAR). Advanced satellite imageries, the latest tools, and techniques need to be incorporated for forest mapping in Pakistan to facilitate forest stakeholders in managing the forests and undertaking national projects like UN’s REDD+ effectively.