Assessment and prediction of index based agricultural drought vulnerability using machine learning algorithms.

The consequences of droughts are far-reaching, impacting the natural environment, water quality, public health, and accelerating economic losses. Applications of remote sensing techniques using satellite imageries can play an influential role in identifying drought severity (DS) and impacts for a broader range of areas. The Barind Tract (BT) is a region of Bangladesh located northwest of the country and considered one of the hottest, semi-arid, and drought-prone regions. This study aims to assess and predict the drought vulnerability over BT using Landsat satellite images from 1996 to 2031. Several indices, including Normalized Difference Vegetation Index (NDVI), Modified Normalized Difference Water Index (MNDWI), Soil Moisture Content (SMC), Temperature Condition Index (TCI), Vegetation Condition Index (VCI), and Vegetation Health Index (VHI). VHI has been used to identify and predict DS based on VCI and TCI characteristics for 2026 and 2031 using Cellular Automata (CA)-Artificial Neural Network (ANN) algorithms. Results suggest an increasing patterns of DS accelerated by the reduction of healthy vegetation (19 %) and surface water bodies (26 %) and increased higher temperature (>5 °C) from 1996 to 2021. In addition, the VHI result signifies a massive increase in extreme drought conditions from 1996 (2 %) to 2021 (7 %). The DS prediction witnessed a possible expansion in extreme and severe drought conditions in 2026 (15 % and 13 %) and 2031 (18 % and 24 %). Understanding the possible impacts of drought will allow planners and decision-makers to initiate mitigating measures for enhancing the communities preparedness to cope with drought vulnerability.

Nasal swab as an alternative specimen for the detection of severe acute respiratory syndrome coronavirus 2.

Background and Aims: The coronavirus disease 2019 (COVID-19) has brought serious threats to public health worldwide. Nasopharyngeal, nasal swabs, and saliva specimens are used to detect severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). However, limited data are available on the performance of less invasive nasal swab for testing COVID-19. This study aimed to compare the diagnostic performance of nasal swabs with nasopharyngeal swabs using real-time reverse transcription polymerase chain reaction (RT-PCR) considering viral load, onset of symptoms, and disease severity. Methods: A total of 449 suspected COVIDCOVID-19 individuals were recruited. Both nasopharyngeal and nasal swabs were collected from the same individual. Viral RNA was extracted and tested by real-time RT-PCR. Metadata were collected using structured questionnaire and analyzed by SPSS and MedCalc software. Results: The overall sensitivity of the nasopharyngeal swab was 96.6%, and the nasal swab was 83.4%. The sensitivity of nasal swabs was more than 97.7% for low and moderate C t values. Moreover, the performance of nasal swab was very high (>87%) for hospitalized patients and at the later stage >7 days of onset of symptoms. Conclusion: Less invasive nasal swab sampling with adequate sensitivity can be used as an alternative to nasopharyngeal swabs for the detection of SARS-CoV-2 by real-time RT-PCR.

Predicting changes in land use/land cover and seasonal land surface temperature using multi-temporal landsat images in the northwest region of Bangladesh.

Land use/land cover (LULC) variations are accelerated by rapid urbanization and significantly impacted global Land Surface Temperature (LST). The dynamic increase in LST results in the Urban Heat Island (UHI) effect. In this study, future LULC change scenarios, seasonal (summer & winter) LST variations, and LST distribution over different LULC classes were predicted using Landsat satellite images for 1999, 2009, and 2019 in Rajshahi District, Bangladesh. Cellular Automata (CA) and Artificial Neural Network (ANN) procedures were used to predict the LULC changes and seasonal LST variations for 2029 and 2039. In addition, Focus Group Discussions (FGDs) and Key Informants Interviews (KIIs) were conducted to identify the possible impacts of LULC change, LST shifts, and climate change on agricultural productivity and developed a sustainable land use management plan for the study area. Validation of the CA model demonstrated an excellent accuracy with a kappa value of 0.82. Similarly, the ANN model's validation using Mean Square Error (0.523 and 0.796 for summer) and Correlation coefficient (0.6023 and 0.831 for winter) values demonstrated a good prediction accuracy. The LULC prediction result indicated that the built-up area will be expanded by 58.03 km2 and 79.90 km2, respectively, from 2019 to 2029 and 2039. The predicted seasonal LST indicated that in 2029 and 2039, more than 23.30 % and 50.46 % of the summer and 3.02 % and 13.02 % of the winter seasons will likely be experienced LSTs greater than 35 °C. The results of public participation exposed that changes in LULC classes, variations in LST, and climate change significantly impact the regional biodiversity (loss of farmland and water bodies), reduce agricultural productivity, and increase extreme weather events (flood, heavy rainfall, and cold/warm temperature). This study provides the useful guidelines for agricultural officers, urban planners, and environmental engineers to understand the spatial configurations of built-up area enlargement and provide effective policy measures to conserve farming lands to ensure environmental sustainability.