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

Flood resilience through hybrid deep learning: Advanced forecasting for Taipei's urban drainage system

The escalating impacts of climate change have intensified extreme rainfall events, placing urban drainage systems under unprecedented pressure and increasing flood risks. Addressing these challenges requires advanced flood mitigation strategies, optimized sewer operations, and responsive disaster management. This study leverages knowledge graphs to integrate diverse data sources, providing a comprehensive perspective on flood dynamics, and applies deep learning models within a Real-Time Urban Drainage Early Warning System to enhance flood management at Taipei City's Zhongshan Pumping Station in Taiwan. We proposed deep learning models, specifically Convolutional Neural Networks combined with Back Propagation Neural Networks (CNN-BP), to make multi-input multi-output multi-step (MIMOMS) forecasts on sewer water levels at intervals from 10 to 40 min (T+1 to T+4) and MIMO forecasts on the pumping station's internal (forebay) and external (river) water levels at intervals from 10 to 60 min (T+1 to T+6). The CNN-BP model exhibited superior forecast accuracy, reaching an R2 (RMSE) of 0.97 (0.08m) at T+1 for sewer water levels and an R2 (RMSE) of 0.99 (0.06m) at T+1 for both internal and external water levels. These results highlight CNN-BP's capability to accurately capture water level trends, ensuring reliable real-time responsiveness, especially during intense and sudden rainfall events. The CNN-BP's high predictive accuracy enables enhanced pump operations, strengthens early warning systems, and fosters intelligent flood control practices crucial for effective environmental management.

Light-driven modulation of plant response to water deficit. A review

The dependence of agriculture on water availability is an important premise justifying attempts to enhance water use efficiency for plant production. Photosynthetic efficiency, directly impacts biomass production, is dependent on both water availability and the quality and quantity of light. Understanding how these factors interact is crucial for improving crop yields. Many overlapping signalling pathways and functions of common bioactive molecules that shape plant responses to both water deficit and light have been identified and discussed in this review. Separate or combined action of these environmental factors include the generation of reactive oxygen species, biosynthesis of abscisic acid, stomatal functioning, chloroplast movement and alterations in the levels of photosynthetic pigments and bioactive molecules. Plant response to water deficit depends on light intensity and its characteristics, with differentiated impacts from UV, blue, and red light bands determining the strength and synergistic or antagonistic nature of interactions. Despite its significance, the combined effects of these environmental factors remain insufficiently explored. The findings highlight the potential for optimising horticultural production through controlled light conditions and regulated deficit irrigation. Future research should assess light and water manipulation strategies to enhance resource efficiency and crop nutritional value.

Integration of remote sensing and machine learning algorithm for agricultural drought early warning over Genale Dawa river basin, Ethiopia

Drought remains a menace in the Horn of Africa; as a result, the Ethiopia's Genale Dawa River Basin is one of the most vulnerable to agricultural drought. Hence, this study integrates remote sensing and machine learning algorithm for early warning identification through assessment and prediction of index-based agricultural drought over the basin. To track the severity of the drought in the basin from 2003 to 2023, a range of high-resolution satellite imagery output indexes were used, including the Vegetation Condition Index (VCI), Thermal Condition Index (TCI), and Vegetation Health Index (VHI). Additionally, the Artificial Neural Network machine learning technique was used to predict agricultural drought VHI for the period of 2028 and 2033. Results depict that during the 2023 period, 25% of severe drought and 18% of extreme drought countered at the lower part of the basin at Dolo ado and Chereti regions. A high TCI value was found that around 23.24% under extreme drought and low precipitation countered in areas of Moyale, Dolo ado, Dolobay, Afder, and Bure lower than 3.57 mm per month. Similarly, increment of severe drought from 24.26% to 24.58% and 16.53% to 16.58% of extreme drought value of VHI might be experienced during the 2028 and 2033 period respectively in the area of Mada Wolabu, Dolo ado, Dodola, Gore, Gidir, and Rayitu. The findings of this study are significantly essential for the institutes located particularly in the basin as they will allow them to adapt drought-coping mechanisms and decision-making easily.

Integration of SPEI and machine learning for assessing the characteristics of drought in the middle ganga plain, an agro-climatic region of India

Drought, as a natural and intricate climatic phenomenon, poses challenges with implications for both natural ecosystems and socioeconomic conditions. Evaluating the characteristics of drought is a significant endeavor aimed at mitigating its impact on society and individuals. This research paper explores the integration of the Standardized Precipitation Evapotranspiration Index (SPEI) and machine learning techniques for an assessment of drought characteristics in the Middle Ganga Plain, a crucial agro-climatic region in India. The study focuses on evaluating the frequency, intensity, magnitude, and recurrence interval of drought events. Various drought models, including Random Forest (RF), Artificial Neural Networks (ANN), and an ensemble model combining ANN and RF, were employed to analyze and predict drought patterns at different temporal scales (3-month, 6-month, and 12-month). The performance of these models was rigorously validated using key metrics such as precision, accuracy, proportion incorrectly classified, over-all area under the curve (AUC), mean absolute error (MAE), and root mean square error (RMSE). Furthermore, the research extends its application to delineating drought vulnerability zones by establishing demarcations for high and very high drought vulnerability areas for each model and temporal scale. Results indicate that the south-western part of the middle Ganga plain falls under the highly drought-vulnerable zone, which averagely covers 40% of the study region. The core and buffer regions of drought vulnerability have also been identified. The south-western part of the study area is identified as the core region of drought. Ground verification of the drought-vulnerable area has been done by using soil moisture meter. Validation metrics show that the ensemble model of ANN and RF exhibits the highest accuracy across all temporal scales. This research's findings can be applied to improve drought preparedness and water resource management in the Middle Ganga Plain. By identifying high-risk drought zones and utilizing accurate prediction models, policymakers and farmers can implement targeted mitigation strategies. This approach could enhance agricultural resilience, protect livelihoods, and optimize water allocation in this vital agro-climatic region.

Drought vulnerability assessment and its impact on crop production and livelihood of people: An empirical analysis of Barind Tract

North-Western section of Bangladesh is experiencing a protracted decrease in precipitation, irregular rainfall, and the depletion of ground water, which results in water scarcity and extreme dry weather that impedes the production of agricultural commodities and threatens the people's way of life. Analyzing the precipitation deficit and ground water deficit, along with vegetation cover, temperature condition, and the condition of the vegetation is a crucial component of drought vulnerability assessment. Rajshahi Zilla, a region of Bangladesh located in the middle of the Barind tract, is experiencing a severe water shortage. The irregular rainfall, decrease in rainfall, prolonged absence of rainfall and ground water depletion results in drought. This study aims to access the vulnerability of drought by analyzing precipitation rates, ground water depletion levels, temperature condition, vegetation condition and the vegetative droughts to find out the severe condition of droughts and the severe effects of this in the livelihoods of the farmers and their crop production practices. In this case the study focuses on determining NDVI, NDWI, NDMI, VCI, TCI, and VHI. The VHI results show a significant increase in extreme drought conditions from 2013 (4 %) to 2021 (7 %). By conducting a few questionnaire surveys and Focus Group Discussion the present situation of crop production and the livelihoods of people has been analyzed. Almost 18.3 % of farmers have made a permanent move away from agriculture, and 80 % of permanently relocated farmers report an improvement in their quality of life. Nearly 60 % of farmers believe that the construction of deep ditches has enhanced their crop yield. Once again, more than 20 % are in the same predicament as previously, with over 19 % reporting that deep irrigation has lowered agricultural yield. Comprehending the potential consequences of drought will enable planners and decision-makers to implement mitigation measures aimed at improving the communities' ability to manage drought risk. After analyzing data, it has been found that Rajshahi is facing a critical drought problem, which has led to water scarcity, severely affecting agricultural production and livelihoods.

Delineating the drought vulnerability zones in Bangladesh

The research aims to explore the vulnerability of Bangladesh to drought by considering a comprehensive set of twenty-four factors, classified into four major categories: meteorological, hydrological, agricultural, and socioeconomic vulnerability. To achieve this, the study utilized a knowledge-based multi-criteria method known as the Analytic Hierarchy Process (AHP) to delineate drought vulnerability zones across the country. Weight estimation was accomplished by creating pairwise comparison matrices for factors and different types of droughts, drawing on relevant literature, field experience, and expert opinions. Additionally, online-based interviews and group discussions were conducted with 30 national and foreign professionals, researchers, and academics specializing in drought-related issues in Bangladesh. Results from overall drought vulnerability map shows that the eastern hills region displays a notably high vulnerability rate of 56.85% and an extreme low vulnerability rate of 0.03%. The north central region shows substantial vulnerability at high levels (35.85%), while the north east exhibits a significant proportion (41.68%) classified as low vulnerability. The north west region stands out with a vulnerability rate of 40.39%, emphasizing its importance for drought management strategies. The River and Estuary region displays a modest vulnerability percentage (38.44%), suggesting a balanced susceptibility distribution. The south central and south east regions show significant vulnerabilities (18.99% and 39.60%, respectively), while the south west region exhibits notable vulnerability of 41.06%. The resulting model achieved an acceptable level of performance, as indicated by an area under the curve value of 0.819. Policymakers and administrators equipped with a comprehensive vulnerability map can utilize it to develop and implement effective drought mitigation strategies, thereby minimizing the losses associated with drought.

Predicting agricultural and meteorological droughts using Holt Winter Conventional 2D-Long Short-Term Memory (HW-Conv2DLSTM)

Drought is an extended shortage of rainfall resulting in water scarcity and affecting a region's social and economic conditions through environmental deterioration. Its adverse environmental effects can be minimised by timely prediction. Drought detection uses only ground observation stations, but satellite-based supervision scans huge land mass stretches and offers highly effective monitoring. This paper puts forward a novel drought monitoring system using satellite imagery by considering the effects of droughts that devastated agriculture in Thanjavur district, Tamil Nadu, between 2000 and 2022. The proposed method uses Holt Winter Conventional 2D-Long Short-Term Memory (HW-Conv2DLSTM) to forecast meteorological and agricultural droughts. It employs Climate Hazards Group InfraRed Precipitation with Station (CHIRPS) data precipitation index datasets, MODIS 11A1 temperature index, and MODIS 13Q1 vegetation index. It extracts the time series data from satellite images using trend and seasonal patterns and smoothens them using Holt Winter alpha, beta, and gamma parameters. Finally, an effective drought prediction procedure is developed using Conv2D-LSTM to calculate the spatiotemporal correlation amongst drought indices. The HW-Conv2DLSTM offers a better R2 value of 0.97. It holds promise as an effective computer-assisted strategy to predict droughts and maintain agricultural productivity, which is vital to feed the ever-increasing human population.

Regional characterization of meteorological and agricultural drought in Baluchistan province, Pakistan

Drought is a complex natural hazard that occurs when a region experiences a prolonged period of dry conditions, leading to water scarcity and negative impacts on the environment. This study analyzed the recurrence of drought and wet spells in Baluchistan province, Pakistan. Reconnaissance Drought Index (RDI), Standardized Precipitation Evapotranspiration Index (SPEI), and Vegetation Condition Index (VCI) were used to analyze droughts in Baluchistan during 1986-2021. Statistical analysis i.e. run theory, linear regression, and correlation coefficient were used to quantify the trend and relationship between meteorological (RDI, SPEI) and agricultural (VCI) droughts. The meteorological drought indices (1, 3, 6, and 12-month RDI and SPEI) identified severe to extreme drought spells during 1986, 1988, 1998, 2000-2002, 2004, 2006, 2010, 2018-2019, and 2021 in most meteorological stations (met-stations). The Lasbella met-station experienced the most frequent extreme to severe droughts according to both the 12-month RDI (8.82%) and SPEI (15.38%) indices. The Dalbandin met-station (8.34%) follows closely behind for RDI, while Khuzdar (5.88%) comes in second for the 12-month SPEI. VCI data showed that Baluchistan experienced severe to extreme drought in 2000, 2001, 2006, and 2010. The most severe drought occurred in 2000 and 2001, affecting 69% of the study region. A positive correlation was indicated between meteorological (RDI, SPEI) and agricultural drought index (VCI). The multivariate indices can provide valuable knowledge about drought episodes and preparedness to mitigate drought impacts.

Harnessing urban analytics and machine learning for sustainable urban development: A multidimensional framework for modeling environmental impacts of urbanization in Saudi Arabia

Sustainable urban development is crucial for managing natural resources and mitigating environmental impacts induced by rapid urbanization. This study demonstrates an integrated framework using machine learning-based urban analytics techniques to evaluate spatiotemporal urban expansion in Saudi Arabia (1987-2022) and quantify impacts on leading land, water, and air-related environmental parameters (EPs). Remote sensing and statistical techniques were applied to estimate vegetation health, built-up area, impervious surface, water bodies, soil characteristics, thermal comfort, air pollutants (PM2.5, CH4, CO, NO2, SO2), and nighttime light EPs. Regression assessment and Principal Component Analysis (PCA) were applied to assess the relationships between urban expansion and EPs. The findings highlight the substantial growth of urban areas (0.067%-0.14%), a decline in soil moisture (16%-14%), water bodies (60%-22%), a nationwide increase of PM2.5 (44 μg/m3 to 73 μg/m3) and night light intensity (0.166-9.670) concentrations resulting in significant impacts on land, water, and air quality parameters. PCA showed vegetation cover, soil moisture, thermal comfort, PM2.5, and NO2 are highly impacted by urban expansion compared to other EPs. The results highlight the need for effective and sustainable interventions to mitigate environmental impacts using green innovations and urban development by applying mixed-use development, green space preservation, green building technologies, and implementing renewable energy approaches. The framework recommended for environmental management in this study provides a robust foundation for evidence-based policies and adaptive management practices that balance economic progress and environmental sustainability. It will also help policymakers and urban planners in making informed decisions and promoting resilient urban growth.

Geo-ecological, shoreline dynamic, and flooding impacts of Cyclonic Storm Mocha: A geospatial analysis

This research comprehensively assesses the aftermath of Cyclonic Storm Mocha, focusing on the coastal zones of Rakhine State and the Chittagong Division, spanning Myanmar and Bangladesh. The investigation emphasizes the impacts on coastal ecology, shoreline dynamics, flooding patterns, and meteorological variations. Employed were multiple vegetation indices-Normalized Difference Vegetation Index (NDVI), Enhanced Vegetation Index (EVI), Modified Vegetation Condition Index (mVCI), Disaster Vegetation Damage Index (DVDI), and Fractional Vegetation Cover (FVC)-to evaluate ecological consequences. The Digital Shoreline Assessment System (DSAS) aided in determining shoreline alterations pre- and post-cyclone. Soil exposure and flood extents were scrutinized using the Bare Soil Index (BSI) and Modified Normalized Difference Water Index (MNDWI), respectively. Additionally, the study encompassed an analysis of microclimatic variables, comparing meteorological data across pre- and post-cyclone periods. Findings indicate significant ecological impacts: an estimated 8985.46 km2 of dense vegetation (NDVI >0.6) was adversely affected. Post-cyclone, there was a discernible reduction in EVI values. The mean mVCI shifted negatively from -0.18 to -0.33, and the mean FVC decreased from 0.39 to 0.33. The DVDI underscored considerable vegetation damage in various areas, underscoring the cyclone's extensive impact. Meteorological analysis revealed a 245 % increase in rainfall (20.22 mm on May 14, 2023 compared to the May average of 5.86 mm), and significant increases in relative humidity (14 %) and wind speed (205 %). Erosion was observed along 74.60 % of the studied shoreline. These insights are pivotal for developing comprehensive strategies aimed at the rehabilitation and conservation of critical coastal ecosystems. They provide vital data for emergency response initiatives and offer resources for entities engaged in enhancing coastal resilience and protecting local community livelihoods.

Identification of influential weather parameters and seasonal drought prediction in Bangladesh using machine learning algorithm

Droughts pose a severe environmental risk in countries that rely heavily on agriculture, resulting in heightened levels of concern regarding food security and livelihood enhancement. Bangladesh is highly susceptible to environmental hazards, with droughts further exacerbating the precarious situation for its 170 million inhabitants. Therefore, we are endeavouring to highlight the identification of the relative importance of climatic attributes and the estimation of the seasonal intensity and frequency of droughts in Bangladesh. With a period of forty years (1981-2020) of weather data, sophisticated machine learning (ML) methods were employed to classify 35 agroclimatic regions into dry or wet conditions using nine weather parameters, as determined by the Standardized Precipitation Evapotranspiration Index (SPEI). Out of 24 ML algorithms, the four best ML methods, ranger, bagEarth, support vector machine, and random forest (RF) have been identified for the prediction of multi-scale drought indices. The RF classifier and the Boruta algorithms shows that water balance, precipitation, maximum and minimum temperature have a higher influence on drought intensity and occurrence across Bangladesh. The trend of spatio-temporal analysis indicates, drought intensity has decreased over time, but return time has increased. There was significant variation in changing the spatial nature of drought intensity. Spatially, the drought intensity shifted from the northern to central and southern zones of Bangladesh, which had an adverse impact on crop production and the livelihood of rural and urban households. So, this precise study has important implications for the understanding of drought prediction and how to best mitigate its impacts. Additionally, the study emphasizes the need for better collaboration between relevant stakeholders, such as policymakers, researchers, communities, and local actors, to develop effective adaptation strategies and increase monitoring of weather conditions for the meticulous management of droughts in Bangladesh.

Differential responses of crop yields to multi-timescale drought in mainland China: Spatiotemporal patterns and climate drivers

Increasingly frequent and severe droughts pose a growing threat to food security in China. However, our understanding of how different crops respond to multi-timescale drought under varying climatic conditions remains limited, hindering effective drought risk management. To address this knowledge gap, we applied spatial principal component analysis (SPCA) to unveil spatiotemporal patterns in annual yields of major grain crops (rice, wheat, maize) and cotton in response to multi-timescale drought, as indicated by the standardized precipitation evapotranspiration index (SPEI) across China. Subsequently, predictive discriminant analysis (PDA) was employed to identify the primary climatic factors driving these response patterns. The findings indicated that drought-induced interannual variability of crop yields were spatially and temporally heterogeneous, closely tied to the timescale used for drought assessment. Crop types displayed distinct responses to drought, evident in the variations of months and corresponding timescales for their strongest reactions. The initial three principal components, capturing over 65 % of drought-related yield variance, unveiled short- to medium-term patterns for rice, maize, and cotton, and long-term patterns for wheat. Specifically, rice was highly susceptible to drought on a 4-month timescale in September, wheat on a 6-month timescale in May, maize on a 3-month timescale in August, and cotton on a 3-month timescale in September. Moreover, the first three discriminant functions explaining over 90 % of the total variance, effectively distinguish spatiotemporal crop yield response patterns to drought. These patterns primarily stem from seasonal climatic averages, with water balance (precipitation minus potential evapotranspiration) and temperature being the most influential variables (p < 0.05). Interestingly, we observed a weak correlation between drought severity and crop yield in humid conditions, with responses tending to manifest over longer timescales. These findings enhance our comprehension of how drought timescales impact crop yields in China, providing valuable insights for the implementation of rational irrigation management strategies.

Machine learning models development for accurate multi-months ahead drought forecasting: Case study of the Great Lakes, North America

The Great Lakes are critical freshwater sources, supporting millions of people, agriculture, and ecosystems. However, climate change has worsened droughts, leading to significant economic and social consequences. Accurate multi-month drought forecasting is, therefore, essential for effective water management and mitigating these impacts. This study introduces the Multivariate Standardized Lake Water Level Index (MSWI), a modified drought index that utilizes water level data collected from 1920 to 2020. Four hybrid models are developed: Support Vector Regression with Beluga whale optimization (SVR-BWO), Random Forest with Beluga whale optimization (RF-BWO), Extreme Learning Machine with Beluga whale optimization (ELM-BWO), and Regularized ELM with Beluga whale optimization (RELM-BWO). The models forecast droughts up to six months ahead for Lake Superior and Lake Michigan-Huron. The best-performing model is then selected to forecast droughts for the remaining three lakes, which have not experienced severe droughts in the past 50 years. The results show that incorporating the BWO improves the accuracy of all classical models, particularly in forecasting drought turning and critical points. Among the hybrid models, the RELM-BWO model achieves the highest level of accuracy, surpassing both classical and hybrid models by a significant margin (7.21 to 76.74%). Furthermore, Monte-Carlo simulation is employed to analyze uncertainties and ensure the reliability of the forecasts. Accordingly, the RELM-BWO model reliably forecasts droughts for all lakes, with a lead time ranging from 2 to 6 months. The study's findings offer valuable insights for policymakers, water managers, and other stakeholders to better prepare drought mitigation strategies.

Quantifying climate variability and regional anthropogenic influence on vegetation dynamics in northwest India

To explore the spatio-temporal dynamics and mechanisms underlying vegetation cover in Haryana State, India, and implications thereof, we obtained MODIS EVI imagery together with CHIRPS rainfall and MODIS LST at annual, seasonal and monthly scales for the period spanning 2000 to 2022. Additionally, MODIS Potential Evapotranspiration (PET), Ground Water Storage (GWS), Soil Moisture (SM) and nighttime light datasets were compiled to explore their spatial relationships with vegetation and other selected environmental parameters. Non-parametric statistics were applied to estimate the magnitude of trends, along with correlation and residual trend analysis to quantify the relative influence of Climate Change (CC) and Human Activities (HA) on vegetation dynamics using Google Earth Engine algorithms. The study reveals regional contrasts in trends that are evidently related to elevation. An annual increasing trend in rainfall (21.3 mm/decade, p < 0.05), together with augmented vegetation cover and slightly cooler (-0.07 °C/decade) LST is revealed in the high-elevation areas. Meanwhile, LST in the plain regions exhibit a warming trend (0.02 °C/decade) and decreased in vegetation and rainfall, accompanied by substantial reductions in GWS and SM related to increased PET. Linear regression demonstrates a strongly significant relationship between rainfall and EVI (R2 = 0.92), although a negative relationship is apparent between LST and vegetation (R2 = -0.83). Additionally, increased LST in the low-elevation parts of the study area impacted PET (R2 = 0.87), which triggered EVI loss (R2 = 0.93). Moreover, increased HA resulted in losses of 25.5 mm GSW and 1.5 mm SM annually. The relative contributions of CC and HA are shown to vary with elevation. At higher elevations, CC and HA contribute respectively 85% and 15% to the increase in EVI. However, at lower elevations, reduced EVI is largely (79%) due to human activities. This needs to be considered in managing the future of vulnerable socio-ecological systems in the state of Haryana.

Quantifying irrigation water demand and supply gap using remote sensing and GIS in Multan, Pakistan

Human interventions and rapid changes in land use adversely affect the adequate distribution of water resources. A research study was conducted to quantify the gap between demand and supply for irrigation water in Multan, Pakistan, which may lead to sustainable water management. Two remotely sensed images (Landsat 8 OLI and Landsat 5 TM) were downloaded for the years 2010 and 2020, and supervised classification method was performed for the selected land use land cover (LULC) classes and basic framework. During the evaluation, the kappa coefficient was found in the ranges of 0.83-0.85, and overall accuracy was found to be more than 80% which indicated a substantial agreement between the classified maps and the ground truth data for both years and seasons. The LULC maps showed that urbanization has increased by 49% during the last decade (2010-2020). Reduction in planting areas for wheat (9%), cotton (24%), and orchards (46%) was observed. An increase in planting areas for rice (92%) and sugarcane (63%) was observed. The changing LULC pattern may be related to variation in water demand and supply for irrigation. The irrigation water demand has decreased by 370.2 Mm3 from 2010 to 2020, due to the reduction in agricultural land and an increase in urbanization. Available irrigation water supply (canals/rainfall) was estimated as 2432 Mm3 for the year 2020 which was 26% less than that of total irrigation water demand (3281 Mm3). The findings also provide the database for sustainable water management and equitable distribution of water in the region.

The COP27 screened through the lens of global water security

Water security is an expression of resilience. In the recent past, scientists and public organizations have built considerable work around this concept launched in 2013 by the United Nations as "the capacity of a population to safeguard sustainable access to adequate quantities of acceptable quality water for sustaining livelihoods, human well-being, and socio-economic development, for ensuring protection against water-borne pollution and water-related disasters, and for preserving ecosystems in a climate of peace and political stability". In the 27th Conference of the Parties (COP27), held in Sharm El-Sheikh (Egypt) in last November, water security was considered a priority in the climate agenda, especially in the adaption and loss and damage axes. This discussion paper represents the authors' opinion about how the conference coped with water security and what challenges remain to attend. As discussion paper, it had the purpose to stimulate further discussion in a broader scientific forum.