Worldwide, the persistent trend of human and animal life losses, as well as damage to properties due to wildlife–vehicle collisions (WVCs) remains a significant source of concerns for a broad range of stakeholders. To mitigate their occurrences and impact, many approaches are being adopted, with varying successes. Because of their increased versatility and increasing efficiency, Artificial Intelligence-based methods have been experiencing a significant level of adoption. The present work extensively reviews the literature on intelligent systems incorporating sensor technologies and/or machine learning methods to mitigate WVCs. Included in our review is an investigation of key factors contributing to human–wildlife conflicts, as well as a discussion of dominant state-of-the-art datasets used in the mitigation of WVCs. Our study combines a systematic review with bibliometric analysis. We find that most animal detection systems (excluding autonomous vehicles) are relying neither on state-of-the-art datasets nor on recent breakthrough machine learning approaches. We, therefore, argue that the use of the latest datasets and machine learning techniques will minimize false detection and improve model performance. In addition, the present work covers a comprehensive list of associated challenges ranging from failure to detect hotspot areas to limitations in training datasets. Future research directions identified include the design and development of algorithms for real-time animal detection systems. The latter provides a rationale for the applicability of our proposed solutions, for which we designed a continuous product development lifecycle to determine their feasibility.

Baryon Acoustic Oscillation (BAO) surveys will be a leading method for addressing the dark energy challenge in the next decade. We explore in detail the effect of allowing for small amplitude admixtures of general isocurvature perturbations in addition to the dominant adiabatic mode. We find that non-adiabatic initial conditions leave the sound speed unchanged but instead excite different harmonics. These harmonics couple differently to Silk damping, altering the form and evolution of acoustic waves in the baryon-photon fluid prior to decoupling. This modifies not only the scale on which the sound waves imprint onto the baryon distribution, which is used as the standard ruler in BAO surveys, but also the shape, width and height of the BAO peak. We discuss these effects in detail and show how more general initial conditions impact our interpretation of cosmological data in dark energy studies. We find that the inclusion of these additional isocurvature modes leads to a decrease in the Dark Energy Task Force figure of merit (FoM) by 46% i.e., FoM_ISO = 0.54 × FoM_AD and 53% for the BOSS and ADEPT experiments respectively when considered in conjunction with PLANK data. We also show that the incorrect assumption of adiabaticity has the potential to bias our estimates of the dark energy parameters by 2.7σ (2.2σ) for a single correlated isocurvature mode (CDM isocurvature), and up to 4.9σ (5.7σ) for three correlated isocurvature modes in the case of the BOSS (ADEPT) experiment. We find that the use of the large scale structure data in conjunction with CMB data improves our ability to measure the contributions of different modes to the initial conditions by as much as 95% for certain modes in the fully correlated case.

On the African continent, South Africa has world-class astronomical facilities for advanced radio astronomy research. With the advent of the Square Kilometre Array project in South Africa (SA SKA), six countries in Africa (SA SKA partner countries) have joined South Africa to contribute towards the African Very Long Baseline Interferometry (VLBI) Network (AVN). Each of the AVN countries aims to construct a single-dish radio telescope that will be part of the AVN, the European VLBI Network, and the global VLBI network. The SKA and the AVN will enable very high sensitivity VLBI in the southern hemisphere. In the current AVN, there is a gap in the coverage in the central African region. This work analyses the increased scientific impact of having additional antennas in each of the six countries in central Africa, i.e., Cameroon, Gabon, Congo, Equatorial Guinea, Chad, and the Central African Republic. A number of economic human capital impacts of having a radio interferometer in central Africa are also discussed. This work also discusses the recent progress on the AVN project and shares a few lessons from some past successes in ground stations retrofitting.

The seasonal autoregressive integrated moving average with exogenous factors (SARIMAX) has shown promising results in modeling small and sparse observed time-series data by capturing linear features using independent and dependent variables. Long short-term memory (LSTM) is a promising neural network for learning nonlinear dependence features from data. With the increase in wildlife roadkill patterns, the SARIMAX-only and LSTM-only models would likely fail to learn the precise endogenous and/or exogenous variables driven by this wildlife roadkill data. In this paper, we design and implement an error correction mathematical framework based on LSTM-only. The framework extracts features from the residual error generated by a SARIMAX-only model. The learned residual features correct the output time-series prediction of the SARIMAX-only model. The process combines SARIMAX-only predictions and LSTM-only residual predictions to obtain a hybrid SARIMAX-LSTM. The models are evaluated using South African wildlife–vehicle collision datasets, and the experiments show that compared to single models, SARIMAX-LSTM increases the accuracy of a taxon whose linear components outweigh the nonlinear ones. In addition, the hybrid model fails to outperform LSTM-only when a taxon contains more nonlinear components rather than linear components. Our assumption of the results is that the collected exogenous and endogenous data are insufficient, which limits the hybrid model’s performance since it cannot accurately detect seasonality on residuals from SARIMAX-only and minimize the SARIMAX-LSTM error. We conclude that the error correction framework should be preferred over single models in wildlife time-series modeling and predictions when a dataset contains more linear components. Adding more related data may improve the prediction performance of SARIMAX-LSTM.