scholarly journals Projecting armed conflict risk in Africa towards 2050 along the SSP-RCP scenarios: a machine learning approach

2021 ◽  
Author(s):  
Jannis M. Hoch ◽  
Sophie P. de Bruin ◽  
Halvard Buhaug ◽  
Nina von Uexkull ◽  
Rens van Beek ◽  
...  
Keyword(s):  
Machine Learning ◽  
Armed Conflict ◽  
Central Africa ◽  
Climatic Conditions ◽  
Eastern Africa ◽  
Rcp Scenarios ◽  
Western Africa ◽  
Out Of Sample ◽  
Conflict Risk ◽  
The One

Abstract In the past decade, several efforts have been made to project armed conflict risk into the future. This study broadens current approaches by presenting a first-of-its-kind application of machine learning (ML) methods to project sub-national armed conflict risk over the African continent along three Shared Socioeconomic Pathway (SSP) scenarios and three Representative Concentration Pathways (RCPs) towards 2050. Results of the open-source ML framework CoPro are consistent with the underlying socioeconomic storylines of the SSPs, and the resulting out-of-sample armed conflict projections obtained with Random Forest classifiers agree with the patterns observed in comparable studies. In SSP1-RCP2.6, conflict risk is low in most regions although the Horn of Africa and parts of East Africa continue to be conflict-prone. Conflict risk increases in the more adverse SSP3-RCP6.0 scenario, especially in Central Africa and large parts of Western Africa. We specifically assessed the role of hydro-climatic indicators as drivers of armed conflict. Overall, their importance is limited compared to main conflict predictors but results suggest that changing climatic conditions may both increase and decrease conflict risk, depending on the location: in Northern Africa and large parts of Eastern Africa climate change increases projected conflict risk whereas for areas in the West and northern part of the Sahel shifting climatic conditions may reduce conflict risk. With our study being at the forefront of machine learning (ML) applications for conflict risk projections, we identify various challenges for this arising scientific field. A major concern is the limited selection of relevant quantified indicators for the SSPs at present. Nevertheless, ML models such as the one presented here are a viable and scalable way forward in the field of armed conflict risk projections, and can help to inform the policy-making process with respect to climate security.

scholarly journals Projecting armed conflict risk in Africa towards 2050 along the Shared Socio-economic Pathways: a machine learning approach

2021 ◽  
Author(s):  
Jannis Hoch ◽  
Sophie de Bruin ◽  
Halvard Buhaug ◽  
Nina von Uexkull ◽  
Rens van Beek ◽  
...  
Keyword(s):  
Machine Learning ◽  
Armed Conflict ◽  
Central Africa ◽  
Data Availability ◽  
Western Africa ◽  
Machine Learning Approach ◽  
Out Of Sample ◽  
Change Impact ◽  
Conflict Risk ◽  
The One

In the past decade, several efforts have been made to project armed conflict risk into the future. One arising technique is the use of machine-learning (ML) models. In this study we explore its opportunities to project sub-national armed conflict risk for three shared socio-economic pathway (SSP) scenarios and three Representative Concentration Pathways (RCPs) by 2040-2050 in Africa, using the novel and open-source ML framework CoPro. Results are consistent with the underlying socio-economic storylines of the SSPs, and the resulting out-of-sample armed conflict projections obtained with RandomForest classifiers agree with comparable studies. In SSP1-RCP2.6, conflict risk is low or absent in most regions, although the Horn of Africa and parts of Kenya, Tanzania and Mozambique continue to be conflict-prone. Conflict risk intensifies in the more severe SSP3-RCP6.0 scenario, especially in central Africa and large parts of western Africa. We specifically assessed the role of hydro-climatic indicators as drivers of armed conflict. Overall, their importance is limited but can differ locally depending on the overall sign of climate change impact and the contextual (socio-economic) factors defining the overall magnitude of those impacts. With our study being at the forefront of ML applications for conflict risk projections, we have identified various challenges for this arising scientific field. A major concern is the inconsistent data availability of observed conflict events as well as of socio-economic indicators for the various SSPs. Nevertheless, ML models such as the one presented here are a viable way forward in the field of armed conflict risk projections, and can help to inform the policy-making process with respect to climate security.

scholarly journals COVID-19 pandemic in the African continent: Forecasts of cumulative cases, new infections, and mortality

2020 ◽  
Author(s):  
T Achoki ◽  
U Alam ◽  
L Were ◽  
T Gebremedhin ◽  
F Senkubuge ◽  
...  
Keyword(s):  
Central Africa ◽  
Population Level ◽  
Eastern Africa ◽  
Local Context ◽  
African Countries ◽  
Enabling Factors ◽  
Western Africa ◽  
Incidence And Mortality ◽  
The Impact ◽  
Mortality Estimates

BackgroundThe epidemiology of COVID-19 remains speculative in Africa. To the best of our knowledge, no study, using robust methodology provides its trajectory for the region or accounts for local context. This paper is the first systematic attempt to provide prevalence, incidence, and mortality estimates across Africa.MethodsCaseloads and incidence forecasts are from a co-variate-based instrumental variable regression model. Fatality rates from Italy and China were applied to generate mortality estimates after making relevant health system and population-level characteristics related adjustments between each of the African countries.ResultsBy June 30 2020, around 16.3 million people in Africa will contract COVID-19 (95% CI 718,403 to 98,358,799). Northern and Eastern Africa will be the most and least affected areas. Cumulative cases by June 30 are expected to reach around 2.9 million (95% CI 465,028 to 18,286,358) in Southern Africa, 2.8 million (95% CI 517,489 to 15,056,314) in Western Africa, and 1.2 million (95% CI 229,111 to 6,138,692) in Central Africa. Incidence for the month of April 2020 is expected to be highest in Djibouti, 32.8 per 1000 (95% CI 6.25 to 171.77), while Morocco will experience among the highest fatalities (1,045 deaths, 95% CI 167 to 6,547).ConclusionLess urbanized countries with low levels of socio-economic development (hence least connected to the world), are likely to register lower and slower transmissions at the early stages of an epidemic. However, the same enabling factors that worked for their benefit can hinder interventions that have lessened the impact of COVID-19 elsewhere.

scholarly journals The Impact of Advertising and R&D on Bankruptcy Survival: A Double-Edged Sword

2020 ◽  
Vol 84 (5) ◽  
pp. 22-40
Author(s):  
Niket Jindal
Keyword(s):  
Machine Learning ◽  
Research And Development ◽  
Cash Flow ◽  
The Other ◽  
Cumulative Effects ◽  
Future Cash Flow ◽  
Low Level ◽  
Out Of Sample ◽  
The One ◽  
The Impact

Advertising and research and development (R&D) benefit firms by increasing sales and shareholder value. However, when a firm is in bankruptcy, the cumulative effects of its past advertising and R&D can be a double-edged sword. On the one hand, they increase the firm’s expected future cash flow, which increases the likelihood that the bankruptcy court will decide the firm can survive. On the other hand, they increase the liquidation value of the firm’s assets, which decreases the likelihood that the bankruptcy court will decide that the firm can survive. The author argues that the ability of advertising and R&D to either increase or decrease bankruptcy survival is contingent on the influence that the firm’s suppliers have, relative to other creditors, on the bankruptcy court’s decision. Advertising and R&D increase (decrease) bankruptcy survival when suppliers have a high (low) level of influence. Empirical analyses, conducted on 1,504 bankruptcies, show that advertising (R&D) increases bankruptcy survival when at least 35%−38% (18%−21%) of the bankrupt firm’s debt has been borrowed from suppliers, whereas it decreases bankruptcy survival below this point. Out-of-sample machine learning validation shows that the ability to predict whether a bankrupt customer will survive is substantially improved by considering the firm’s advertising and R&D.

Investigation of the natural ventilation of wind catchers with different geometries in arid region houses

2020 ◽  
Vol 14 (3) ◽  
pp. 7109-7124
Author(s):  
Nasreddine Sakhri ◽  
Younes Menni ◽  
Houari Ameur ◽  
Ali J. Chamkha ◽  
Noureddine Kaid ◽  
...  
Keyword(s):  
Arid Region ◽  
Natural Ventilation ◽  
Reduction Rate ◽  
Internal Flow ◽  
Climatic Conditions ◽  
Maximum Pressure ◽  
Ventilation Technique ◽  
Window Position ◽  
The One ◽  
Flow Velocities

The wind catcher or wind tower is a natural ventilation technique that has been employed in the Middle East region and still until nowadays. The present paper aims to study the effect of the one-sided position of a wind catcher device against the ventilated space or building geometry and its natural ventilation performance. Four models based on the traditional design of a one-sided wind catcher are studied and compared. The study is achieved under the climatic conditions of the South-west of Algeria (arid region). The obtained results showed that the front and Takhtabush’s models were able to create the maximum pressure difference (ΔP) between the windward and leeward of the tower-house system. Internal airflow velocities increased with the increase of wind speed in all studied models. For example, at Vwind = 2 m/s, the internal flow velocities were 1.7, 1.8, 1.3, and 2.5 m/s for model 1, 2, 3, and 4, respectively. However, at Vwind = 6 m/s, the internal flow velocities were 5.6, 5.5, 2.5, and 7 m/s for model 1, 2, 3, and 4, respectively. The higher internal airflow velocities are given by Takhtabush, traditional, front and middle tower models, respectively, with a reduction rate between the tower outlet and occupied space by 72, 42, 36, and 33% for the middle tower, Takhtabush, traditional tower, and the front model tower, respectively. This reduction is due to the due to internal flow resistance. The third part of the study investigates the effect of window (exist opening) position on the opposite wall. The upper, middle and lower window positions are studied and compared. The air stagnation or recirculation zone inside the ventilated space reduced from 55% with the lower window to 46% for the middle window and reached 35% for the upper window position. The Front and Takhtabush models for the one-sided wind catcher with an upper window position are highly recommended for the wind-driven natural ventilation in residential houses that are located in arid regions.

Land Warfare

2018 ◽  
Author(s):  
Christopher Tuck
Keyword(s):  
Armed Conflict ◽  
Modern System ◽  
The One ◽  
Over Time

This chapter charts the key developments in European land warfare since 1900. On the one hand, it is possible to identify overarching explanatory ideas, metanarratives, that can be used to identify continuities in development over time across Europe’s armies. These include the concept of ‘modern system’ land warfare and the ‘transformation paradigm’. However, as this chapter also shows, these two points of continuity do not mean either that European armies are homogenous, or that their conceptual assumptions are uncontested. European land warfare remains a heterogeneous phenomenon, shaped by the variety in national contexts and by contending debates on how appropriate Europe’s armies are to the actual challenges of contemporary and future armed conflict.

scholarly journals Machine Learning in Futures Markets

2021 ◽  
Vol 14 (3) ◽  
pp. 119
Author(s):  
Fabian Waldow ◽  
Matthias Schnaubelt ◽  
Christopher Krauss ◽  
Thomas Günter Fischer
Keyword(s):  
Machine Learning ◽  
Futures Markets ◽  
Learning Models ◽  
Cross Sectional ◽  
Data Set ◽  
Statistical Arbitrage ◽  
Out Of Sample ◽  
Sample Testing ◽  
Arbitrage Strategy ◽  
Machine Learning Models

In this paper, we demonstrate how a well-established machine learning-based statistical arbitrage strategy can be successfully transferred from equity to futures markets. First, we preprocess futures time series comprised of front months to render them suitable for our returns-based trading framework and compile a data set comprised of 60 futures covering nearly 10 trading years. Next, we train several machine learning models to predict whether the h-day-ahead return of each future out- or underperforms the corresponding cross-sectional median return. Finally, we enter long/short positions for the top/flop-k futures for a duration of h days and assess the financial performance of the resulting portfolio in an out-of-sample testing period. Thereby, we find the machine learning models to yield statistically significant out-of-sample break-even transaction costs of 6.3 bp—a clear challenge to the semi-strong form of market efficiency. Finally, we discuss sources of profitability and the robustness of our findings.

Modeling soil temperature using air temperature features in diverse climatic conditions with complementary machine learning models

2021 ◽  
Vol 185 ◽  
pp. 106158
Author(s):  
Maryam Bayatvarkeshi ◽  
Suraj Kumar Bhagat ◽  
Kourosh Mohammadi ◽  
Ozgur Kisi ◽  
M. Farahani ◽  
...  
Keyword(s):  
Machine Learning ◽  
Soil Temperature ◽  
Air Temperature ◽  
Climatic Conditions ◽  
Learning Models ◽  
Machine Learning Models

scholarly journals Analysis of Risk Factors in Dementia Through Machine Learning

2020 ◽  
pp. 1-17
Author(s):  
Francisco Javier Balea-Fernandez ◽  
Beatriz Martinez-Vega ◽  
Samuel Ortega ◽  
Himar Fabelo ◽  
Raquel Leon ◽  
...  
Keyword(s):  
Machine Learning ◽  
Optimization Algorithms ◽  
Progressive Increase ◽  
Control Group ◽  
Data Sets ◽  
Modifiable Factors ◽  
Validation Set ◽  
The One ◽  
And Control ◽  
Potential Tool

Background: Sociodemographic data indicate the progressive increase in life expectancy and the prevalence of Alzheimer’s disease (AD). AD is raised as one of the greatest public health problems. Its etiology is twofold: on the one hand, non-modifiable factors and on the other, modifiable. Objective: This study aims to develop a processing framework based on machine learning (ML) and optimization algorithms to study sociodemographic, clinical, and analytical variables, selecting the best combination among them for an accurate discrimination between controls and subjects with major neurocognitive disorder (MNCD). Methods: This research is based on an observational-analytical design. Two research groups were established: MNCD group (n = 46) and control group (n = 38). ML and optimization algorithms were employed to automatically diagnose MNCD. Results: Twelve out of 37 variables were identified in the validation set as the most relevant for MNCD diagnosis. Sensitivity of 100%and specificity of 71%were achieved using a Random Forest classifier. Conclusion: ML is a potential tool for automatic prediction of MNCD which can be applied to relatively small preclinical and clinical data sets. These results can be interpreted to support the influence of the environment on the development of AD.

scholarly journals IIMLP: integrated information-entropy-based method for LncRNA prediction

2021 ◽  
Vol 22 (S3) ◽  
Author(s):  
Junyi Li ◽  
Huinian Li ◽  
Xiao Ye ◽  
Li Zhang ◽  
Qingzhe Xu ◽  
...  
Keyword(s):  
Machine Learning ◽  
Dna Sequences ◽  
Information Entropy ◽  
Area Under The Curve ◽  
Prediction Method ◽  
Machine Learning Algorithms ◽  
Reading Frame ◽  
Non Coding Rna ◽  
The One ◽  
Long Non Coding Rna

Abstract Background The prediction of long non-coding RNA (lncRNA) has attracted great attention from researchers, as more and more evidence indicate that various complex human diseases are closely related to lncRNAs. In the era of bio-med big data, in addition to the prediction of lncRNAs by biological experimental methods, many computational methods based on machine learning have been proposed to make better use of the sequence resources of lncRNAs. Results We developed the lncRNA prediction method by integrating information-entropy-based features and machine learning algorithms. We calculate generalized topological entropy and generate 6 novel features for lncRNA sequences. By employing these 6 features and other features such as open reading frame, we apply supporting vector machine, XGBoost and random forest algorithms to distinguish human lncRNAs. We compare our method with the one which has more K-mer features and results show that our method has higher area under the curve up to 99.7905%. Conclusions We develop an accurate and efficient method which has novel information entropy features to analyze and classify lncRNAs. Our method is also extendable for research on the other functional elements in DNA sequences.

Pre-Katangan geochronology of Zambia and adjacent parts of Central Africa

1968 ◽  
Vol 5 (3) ◽  
pp. 621-628 ◽  
Author(s):  
J. R. Vail ◽  
N. J. Snelling ◽  
D. C. Rex
Keyword(s):  
Lake Tanganyika ◽  
Central Africa ◽  
New Age ◽  
Orogenic Belt ◽  
Eastern Africa ◽  
Sedimentary Sequence ◽  
Precambrian Rocks ◽  
Late Precambrian ◽  
Orogenic Belts ◽  
Age Determinations

The significance of new age determinations on pre-Katangan (Late Precambrian) rocks and minerals from Zambia and adjacent parts of Tanzania and Rhodesia is discussed. In northwestern Rhodesia, the Lomagundi-Piriwiri sediments were deposited between 2500 and 2000 m.y. ago and were folded along meridional trends at circa 1940 m.y. A later episode of folding and metamorphism along similar trends occurred about 1700 m.y. ago, but only affected the western part of the sedimentary sequence (the Piriwiri Series). This latter date is comparable to that which appears to characterize the Tumbide trend, a N- to NE-trending fold system, in Zambia.In Zambia the Tumbide trend is the oldest tectonic episode preserved in the basement and is found only in isolated blocks and cores into which later tectonisms have not penetrated. The dominant pre-Katangan tectonism is represented by the NE to ENE Irumide trend. Such tectonic trends are particularly well developed in the Irumide Orogenic Belt of northern Zambia and adjacent Tanzania. Age determinations set a younger limit of circa 900 m.y. to this trend and the existence of an Irumide Cycle between about 1600 and 900 m.y. is suggested. The possibility that the relatively unmetamorphosed sediments of the Upper Plateau Series and Abercorn Sandstones at the southern end of Lake Tanganyika, the Mafingi Series of northern Malawi, and the Konse Series of Tanzania, represent near-contemporaneous platform deposition associated with the Irumide belt is considered.From this and other recent studies the distribution of orogenic belts in central and eastern Africa can be revised and a number of features of their pattern and inter-relationships noted.

Sign in / Sign up

Export Citation Format

Share Document