Drought-induced stress represents a significant challenge to agricultural production, exerting adverse effects on both plant growth and overall productivity. Therefore, the exploration of innovative long-term approaches for addressing drought stress within agriculture constitutes a crucial objective, given its vital role in enhancing food security. This article explores the potential use of Trichoderma, a well-known genus of plant growth-promoting fungi, to enhance plant tolerance to drought stress. Trichoderma species have shown remarkable potential for enhancing plant growth, inducing systemic resistance, and ameliorating the adverse impacts of drought stress on plants through the modulation of morphological, physiological, biochemical, and molecular characteristics. In conclusion, the exploitation of Trichoderma's potential as a sustainable solution to enhance plant drought tolerance is a promising avenue for addressing the challenges posed by the changing climate. The manifold advantages of Trichoderma in promoting plant growth and alleviating the effects of drought stress underscore their pivotal role in fostering sustainable agricultural practices and enhancing food security.
This study introduces ensemble empirical mode decomposition (EEMD) coupled with the autoregressive integrated moving average (ARIMA) model for drought prediction. In the realm of drought forecasting, we assess the EEMD-ARIMA model against the traditional ARIMA approach, using monthly precipitation data from January 1970 to December 2019 in Herat province, Afghanistan. Our evaluation spans various timescales of standardized precipitation index (SPI) 3, SPI 6, SPI 9, and SPI 12. Statistical indicators like root-mean-square error, mean absolute error (MAE), mean absolute percentage error (MAPE), and R2 are employed. To comprehend data features thoroughly, each SPI series initially computed from the original monthly precipitation time series. Subsequently, each SPI undergoes decomposition using EEMD, resulting in intrinsic mode functions (IMFs) and one residual series. The next step involves forecasting each IMF component and residual using the corresponding ARIMA model. To create an ensemble forecast for the initial SPI series, the predicted outcomes of the modeled IMFs and residual series are finally added. Results indicate that EEMD-ARIMA significantly enhances drought forecasting accuracy compared to conventional ARIMA model.
Drought affects vegetation growth to a large extent. Understanding the dynamic changes of vegetation during drought is of great significance for agricultural and ecological management and climate change adaptation. The relations between vegetation and drought have been widely investigated, but how vegetation loss and restoration in response to drought remains unclear. Using the standardized precipitation evapotranspiration index (SPEI) and the normalized difference vegetation index (NDVI) data, this study developed an evaluation framework for exploring the responses of vegetation loss and recovery to meteorological drought, and applied it to the humid subtropical Pearl River basin (PRB) in southern China for estimating the loss and recovery of three vegetation types (forest, grassland, cropland) during drought using the observed NDVI changes. Results indicate that vegetation is more sensitive to drought in high-elevation areas (lag time 8 months). Vegetation loss (especially in cropland) is found to be more sensitive to drought duration than drought severity and peak. No obvious linear relationship between drought intensity and the extent of vegetation loss is found. Regardless of the intensity, drought can cause the largest probability of mild loss of vegetation, followed by moderate loss, and the least probability of severe loss. Large spatial variability in the probability of vegetation loss and recovery time is found over the study domain, with a higher probability (up to 50 %) of drought-induced vegetation loss and a longer recovery time (>7 months) mostly in the high-elevation areas. Further analysis suggests that forest shows higher but cropland shows lower drought resistance than other vegetation types, and grassland requires a shorter recovery time (4.2-month) after loss than forest (5.1-month) and cropland (4.8-month).
In the modern world, wheat, a vital global cereal and the second most consumed, is vulnerable to climate change impacts. These include erratic rainfall and extreme temperatures, endangering global food security. Research on hydrogen-rich water (HRW) has gained momentum in plant and agricultural sciences due to its diverse functions. This study examined the effects of different HRW treatment durations on wheat, revealing that the 4-h treatment had the highest germination rate, enhancing potential, vigor, and germination indexes. This treatment also boosted relative water content, root and shoot weight, and average lengths. Moreover, the 4-h HRW treatment resulted in the highest chlorophyll and soluble protein concentrations in seeds while reducing cell death. The 4-h and 5-h HRW treatments significantly increased H2O2 levels, with the highest NO detected in both root and shoot after 4-h HRW exposure. Additionally, HRW-treated seeds exhibited increased Zn and Fe concentrations, along with antioxidant enzyme activities (CAT, SOD, APX) in roots and shoots. These findings suggest that HRW treatment could enhance wheat seed germination, growth, and nutrient absorption, thereby increasing agricultural productivity. Molecular analysis indicated significant upregulation of the Dreb1 gene with a 4-h HRW treatment. Thus, it shows promise in addressing climate change effects on wheat production. Therefore, HRW treatment could be a hopeful strategy for enhancing wheat plant drought tolerance, requiring further investigation (field experiments) to validate its impact on plant growth and drought stress mitigation.
This paper aims to select the most appropriate rain-based meteorological drought index for detecting drought characteristics and identifying tropical drought events in the Johor River Basin (JRB). Based on a multi-step approach, the study evaluated seven drought indices, including the Rainfall Anomaly Index (RAI), Standardized Precipitation Index (SPI), China-Z Index (CZI), Modified China-Z Index (MCZI), Percent of Normal (PN), Deciles Index (DI), and Z-Score Index (ZSI), based on the CHIRPS rainfall gridded-based datasets from 1981 to 2020. Results showed that CZI, MCZI, SPI, and ZSI outperformed the other indices based on their correlation and linearity (R2 = 0.96-0.99) along with their ranking based on the Compromise Programming Index (CPI). The historical drought evaluation revealed that MCZI, SPI, and ZSI performed similarly in detecting drought events, but SPI was more effective in detecting spatial coverage and the occurrence of 'very dry' and 'extremely dry' drought events. Based on SPI, the study found that the downstream area, north-easternmost area, and eastern boundary of the basin were more prone to higher frequency and longer duration droughts. Furthermore, the study found that prolonged droughts are characterized by episodic drought events, which occur with one to three months of 'relief period' before another drought event occurs. The study revealed that most drought events that coincide with El Niño, positive Indian Ocean Dipole (IOD), and negative Madden-Julian Oscillation (MJO) events, or a combination of these events, may worsen drought conditions. The application of CHIRPS datasets enables better spatiotemporal mapping and prediction of drought for JRB, and the output is pertinent for improving water management strategies and adaptation measures. Understanding spatiotemporal drought conditions is crucial to ensuring sustainable development and policies through better regulation of human activities. The framework of this research can be applied to other river basins in Malaysia and other parts of Southeast Asia.
Drought is a major abiotic stress that influences rice production. Although the transcriptomic data of rice against drought is widely available, the regulation of small open reading frames (sORFs) in response to drought stress in rice is yet to be investigated. Different levels of drought stress have different regulatory mechanisms in plants. In this study, drought stress was imposed on four-leaf stage rice, divided into two treatments, 40% and 30% soil moisture content (SMC). The RNAs of the samples were extracted, followed by the RNA sequencing analysis on their sORF expression changes under 40%_SMC and 30%_SMC, and lastly, the expression was validated through NanoString. A total of 122 and 143 sORFs were differentially expressed (DE) in 40%_SMC and 30%_SMC, respectively. In 40%_SMC, 69 sORFs out of 696 (9%) DEGs were found to be upregulated. On the other hand, 69 sORFs out of 449 DEGs (11%) were significantly downregulated. The trend seemed to be higher in 30%_SMC, where 112 (12%) sORFs were found to be upregulated from 928 significantly upregulated DEGs. However, only 8% (31 sORFs out of 385 DEGs) sORFs were downregulated in 30%_SMC. Among the identified sORFs, 110 sORFs with high similarity to rice proteome in the PsORF database were detected in 40%_SMC, while 126 were detected in 30%_SMC. The Gene Ontology (GO) enrichment analysis of DE sORFs revealed their involvement in defense-related biological processes, such as defense response, response to biotic stimulus, and cellular homeostasis, whereas enriched Kyoto Encyclopedia of Genes and Genomes (KEGG) pathways indicated that DE sORFs were associated with tryptophan and phenylalanine metabolisms. Several DE sORFs were identified, including the top five sORFs (OsisORF_3394, OsisORF_0050, OsisORF_3007, OsisORF_6407, and OsisORF_7805), which have yet to be characterised. Since these sORFs were responsive to drought stress, they might hold significant potential as targets for future climate-resilient rice development.
BACKGROUND: Assessment of segregating populations for their ability to withstand drought stress conditions is one of the best approaches to develop breeding lines and drought tolerant varieties. Bambara groundnut (Vigna subterranea L. Verdc.) is a leguminous crop, capable of growing in low-input agricultural systems in semi-arid areas. An F4 bi-parental segregating population obtained from S19-3 × DodR was developed to evaluate the effect of drought stress on photosynthetic parameters and identify QTLs associated with these traits under drought-stressed and well-watered conditions in a rainout shelter.
RESULTS: Stomatal conductance (gs), photosynthesis rate (A), transpiration rate (E) and intracellular CO2 (Ci) were significantly reduced (p
Agriculture, meteorological, and hydrological drought is a natural hazard which affects ecosystems in the central India of Maharashtra state. Due to limited historical data for drought monitoring and forecasting available in the central India of Maharashtra state, implementing machine learning (ML) algorithms could allow for the prediction of future drought events. In this paper, we have focused on the prediction accuracy of meteorological drought in the semi-arid region based on the standardized precipitation index (SPI) using the random forest (RF), random tree (RT), and Gaussian process regression (GPR-PUK kernel) models. A different combination of machine learning models and variables has been performed for the forecasting of metrological drought based on the SPI-6 and 12 months. Models were developed using monthly rainfall data for the period of 2000-2019 at two meteorological stations, namely, Karanjali and Gangawdi, each representing a geographical region of Upper Godavari river basin area in the central India of Maharashtra state which frequently experiences droughts. Historical data from the SPI from 2000 to 2013 was processed to train the model into machine learning model, and the rest of the 2014 to 2019-year data were used for testing to forecast the SPI and metrological drought. The mean square error (MSE), root mean square error (RMSE), adjusted R2, Mallows' (Cp), Akaike's (AIC), Schwarz's (SBC), and Amemiya's PC were used to identify the best combination input model and best subregression analysis for both stations of SPI-6 and 12. The correlation coefficient ([Formula: see text]), mean absolute error (MAE), root mean square error (RMSE), relative absolute error (RAE), and root relative squared error (RRSE) were used to perform evaluation for SPI-6 and 12 months of both stations with RF, RT, and GPR-PUK kernel models during the training and testing scenarios. The results during testing phase revealed that the RF was found as the best model in forecasting droughts with values of [Formula: see text], MAE, RMSE, RAE (%), and RRSE (%) being 0.856, 0.551, 0.718, 74.778, and 54.019, respectively, for SPI-6 while 0.961, 0.361, 0.538, 34.926, and 28.262, respectively, for SPI-12 scales at Gangawdi station. Further, the respective values of evaluators at Karanjali station were 0.913 and 0.966, 0.541 and 0.386, 0.604 and 0.589, 52.592 and 36.959, and 42.315 and 31.394 for PUK kernel and RT models, respectively, during SPI-6 and SPI-12. Machine learning models are potential drought warning techniques because they take less time, have fewer inputs, and are less sophisticated than dynamic or scientific models.
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.
Drought monitoring is crucial for assessing and mitigating the impacts of water scarcity on various sectors and ecosystems. Although traditional drought monitoring relies on soil moisture data, remote sensing technology has have significantly augmented the capabilities for drought monitoring. This study aims to evaluate the accuracy and applicability of two temperature vegetation drought indices (TVDI), TVDINDVI and TVDIEVI, constructed using the Normalized Difference Vegetation Index (NDVI) and the Enhanced Vegetation Index (EVI) vegetation indices for drought monitoring. Using Guangdong Province as a case, enhanced versions of these indices, developed through Savitzky-Golay filtering and terrain correction were employed. Additionally, Pearson correlation analysis and F-tests were utilized to determine the suitability of the Standardized Precipitation Index (SPI) and the Standardized Precipitation Evapotranspiration Index (SPEI) in correlation with TVDINDVI and TVDIEVI. The results show that TVDINDVI had more meteorological stations passing both significance test levels (P
Time-series data offer a way of investigating the causes driving ecological processes as phenomena. To test for possible differences in water relations between species of different forest structural guilds at Danum (Sabah, NE Borneo), daily stem girth increments (gthi), of 18 trees across six species were regressed individually on soil moisture potential (SMP) and temperature (TEMP), accounting for temporal autocorrelation (in GLS-arima models), and compared between a wet and a dry period. The best-fitting significant variables were SMP the day before and TEMP the same day. The first resulted in a mix of positive and negative coefficients, the second largely positive ones. An adjustment for dry-period showers was applied. Interactions were stronger in dry than wet period. Negative relationships for overstorey trees can be interpreted in a reversed causal sense: fast transporting stems depleted soil water and lowered SMP. Positive relationships for understorey trees meant they took up most water at high SMP. The unexpected negative relationships for these small trees may have been due to their roots accessing deeper water supplies (if SMP was inversely related to that of the surface layer), and this was influenced by competition with larger neighbour trees. A tree-soil flux dynamics manifold may have been operating. Patterns of mean diurnal girth variation were more consistent among species, and time-series coefficients were negatively related to their maxima. Expected differences in response to SMP in the wet and dry periods did not clearly support a previous hypothesis differentiating drought and non-drought tolerant understorey guilds. Trees within species showed highly individual responses when tree size was standardized. Data on individual root systems and SMP at several depths are needed to get closer to the mechanisms that underlie the tree-soil water phenomena in these tropical forests. Neighborhood stochasticity importantly creates varying local environments experienced by individual trees.
Accurate prediction of any type of natural hazard is a challenging task. Of all the various hazards, drought prediction is challenging as it lacks a universal definition and is getting adverse with climate change impacting drought events both spatially and temporally. The problem becomes more complex as drought occurrence is dependent on a multitude of factors ranging from hydro-meteorological to climatic variables. A paradigm shift happened in this field when it was found that the inclusion of climatic variables in the data-driven prediction model improves the accuracy. However, this understanding has been primarily using statistical metrics used to measure the model accuracy. The present work tries to explore this finding using an explainable artificial intelligence (XAI) model. The explainable deep learning model development and comparative analysis were performed using known understandings drawn from physical-based models. The work also tries to explore how the model achieves specific results at different spatio-temporal intervals, enabling us to understand the local interactions among the predictors for different drought conditions and drought periods. The drought index used in the study is Standard Precipitation Index (SPI) at 12 month scales applied for five different regions in New South Wales, Australia, with the explainable algorithm being SHapley Additive exPlanations (SHAP). The conclusions drawn from SHAP plots depict the importance of climatic variables at a monthly scale and varying ranges of annual scale. We observe that the results obtained from SHAP align with the physical model interpretations, thus suggesting the need to add climatic variables as predictors in the prediction model.
While droughts and floods have intensified in recent years, only a handful of studies have assessed their impacts on croplands and production in Southeast Asia. Here, we used the Google Earth Engine to assess the droughts and floods and their impacts on croplands and crop production over 40 years from 1980 to 2019. Using the Palmer Drought Severity Index (PDSI) as the basis for determining the drought and flood levels, and crop damage levels, crop production loss in both the Monsoon Climate Region (MCR) and the Equatorial Climate Region (ECR) of Southeast Asia was assessed over 47,192 grid points with 10 × 10-kilometer resolution. We found that rainfed crops were severely affected by droughts in the MCR and floods in the ECR. About 9.42 million ha and 3.72 million ha of cropland was damaged by droughts and floods, respectively. We estimated a total loss of 20.64 million tons of crop production between 2015 and 2019. Rainfed crops in Thailand, Cambodia, and Myanmar were strongly affected by droughts, whereas Indonesia, the Philippines, and Malaysia were more affected by floods over the same period. Accordingly, four levels of policy interventions were prioritized by considering the geolocated crop damage levels.
In Australia, droughts are recurring events that tremendously affect environmental, agricultural and socio-economic activities. Southern Queensland is one of the most drought-prone regions in Australia. Consequently, a comprehensive drought vulnerability mapping is essential to generate a drought vulnerability map that can help develop and implement drought mitigation strategies. The study aimed to prepare a comprehensive drought vulnerability map that combines drought categories using geospatial techniques and to assess the spatial extent of the vulnerability of droughts in southern Queensland. A total of 14 drought-influencing criteria were selected for three drought categories, specifically, meteorological, hydrological and agricultural. The specific criteria spatial layers were prepared and weighted using the fuzzy analytical hierarchy process. Individual categories of drought vulnerability maps were prepared from their specific indices. Finally, the overall drought vulnerability map was generated by combining the indices using spatial analysis. Results revealed that approximately 79.60% of the southern Queensland region is moderately to extremely vulnerable to drought. The findings of this study were validated successfully through the receiver operating characteristics curve (ROC) and the area under the curve (AUC) approach using previous historical drought records. Results can be helpful for decision makers to develop and apply proactive drought mitigation strategies.
Hyperdiverse tropical rainforests, such as the aseasonal forests in Southeast Asia, are supported by high annual rainfall. Its canopy is dominated by the species-rich tree family of Dipterocarpaceae (Asian dipterocarps), which has both ecological (e.g., supports flora and fauna) and economical (e.g., timber production) importance. Recent ecological studies suggested that rare irregular drought events may be an environmental stress and signal for the tropical trees. We assembled the genome of a widespread but near threatened dipterocarp, Shorea leprosula, and analyzed the transcriptome sequences of ten dipterocarp species representing seven genera. Comparative genomic and molecular dating analyses suggested a whole-genome duplication close to the Cretaceous-Paleogene extinction event followed by the diversification of major dipterocarp lineages (i.e. Dipterocarpoideae). Interestingly, the retained duplicated genes were enriched for genes upregulated by no-irrigation treatment. These findings provide molecular support for the relevance of drought for tropical trees despite the lack of an annual dry season.
Climate change is one of the major challenges societies round the world face at present. Apart from efforts to achieve a reduction of emissions of greenhouse gases so as to mitigate the problem, there is a perceived need for adaptation initiatives urgently. Ecosystems are known to play an important role in climate change adaptation processes, since some of the services they provide, may reduce the impacts of extreme events and disturbance, such as wildfires, floods, and droughts. This role is especially important in regions vulnerable to climate change such as the African continent, whose adaptation capacity is limited by many geographic and socio-economic constraints. In Africa, interventions aimed at enhancing ecosystem services may play a key role in supporting climate change adaptation efforts. In order to shed some light on this aspect, this paper reviews the role of ecosystems services and investigates how they are being influenced by climate change in Africa. It contains a set of case studies from a sample of African countries, which serve the purpose to demonstrate the damages incurred, and how such damages disrupt ecosystem services. Based on the data gathered, some measures which may assist in fostering the cause of ecosystems services are listed, so as to cater for a better protection of some of the endangered Africa ecosystems, and the services they provide.
Environmental or abiotic stresses are a common threat that remains a constant and common challenge to all plants. These threats whether singular or in combination can have devastating effects on plants. As a semiaquatic plant, rice succumbs to the same threats. Here we systematically look into the involvement of salicylic acid (SA) in the regulation of abiotic stress in rice. Studies have shown that the level of endogenous salicylic acid (SA) is high in rice compared to any other plant species. The reason behind this elevated level and the contribution of this molecule towards abiotic stress management and other underlying mechanisms remains poorly understood in rice. In this review we will address various abiotic stresses that affect the biochemistry and physiology of rice and the role played by SA in its regulation. Further, this review will elucidate the potential mechanisms that control SA-mediated stress tolerance in rice, leading to future prospects and direction for investigation.
Rice which belongs to the grass family is vulnerable to water stress. As water resources get limited, the productivity of rice is affected especially in granaries located at drought prone areas. It would be even worse in granaries located in drought prone areas such as KADA that receives the lowest rainfall in Malaysia. Spermine (SPM), a polyamine compound that is found ubiquitiosly in plants is involved in adaptation of biotic and abiotic stresses. The effect of SPM on growth,grain filling and yield of rice at three main granaries namely, IADA BLS, MADA and KADA representing unlimited water, limited water and water stress conditions respectively, were tested during the main season. Additinally, the growth enhancer was also tested during off season at KADA. Spermine increased plant height, number of tillers per hill and chlorophyll content in all three granaries. Application of SPM improved yield by 38, 29 and 20% in MADA, KADA and IADA BLS, respectively. Harvest index showed 2.6, 6 and 16% increases at IADA BLS, KADA and MADA, respectively in SPM treated plants as compared to untreated. Except for KADA which showed a reduction in yield at 2.54 tha-1, SPM improved yield at MADA, 7.21 tha-1 and IADA BLS, 9.13 tha-1 as compared to the average yield at these respective granaries. In the second trial, SPM increased the yield to 7.0 and 6.4 tha-1 during main and off seasons, respectively, indicating that it was significantly higher than control and the average yield reported by KADA. The yield of SPM treatments improved by 25 and 33% with an increment of farmer's income at main and off seasons, respectively. Stomatal width was significantly higher than control at 11.89 µm. In conclusion, irrespective of the tested granaries and rice variety, spermine mediated plots displayed increment in grain yield.
Rice is an important grain that is the staple food for most of the world's population. Drought is one of the major stresses that negatively affects rice yield. The nature of drought tolerance in rice is complex as it is determined by various components and has low heritability. Therefore, to ensure success in breeding programs for drought tolerant rice, QTLs (quantitative trait loci) of interest must be stable in a variety of plant genotypes and environments. This study identified stable QTLs in rice chromosomes in a variety of backgrounds and environments and conducted a meta-QTL analysis of stable QTLs that have been reported by previous research for use in breeding programs. A total of 653 QTLs for drought tolerance in rice from 27 genetic maps were recorded for analysis. The QTLs recorded were related to 13 traits in rice that respond to drought. Through the use of BioMercartor V4.2, a consensus map containing QTLs and molecular markers were generated using 27 genetic maps that were extracted from the previous 20 studies and meta-QTL analysis was conducted on the consensus map. A total of 70 MQTLs were identified and a total of 453 QTLs were mapped into the meta-QTL areas. Five meta-QTLs from chromosome 1 (MQTL 1.5 and MQTL 1.6), chromosome 2 (MQTL2.1 and MQTL 2.2) and chromosome 3 (MQTL 3.1) were selected for functional annotation as these regions have high number of QTLs and include many traits in rice that respond to drought. A number of genes in MQTL1.5 (268 genes), MQTL1.6 (640 genes), MQTL 2.1 (319 genes), MQTL 2.2 (19 genes) and MQTL 3.1 (787 genes) were annotated through Blast2GO. Few major proteins that respond to drought stress were identified in the meta-QTL areas which are Abscisic Acid-Insensitive Protein 5 (ABI5), the G-box binding factor 4 (GBF4), protein kinase PINOID (PID), histidine kinase 2 (AHK2), protein related to autophagy 18A (ATG18A), mitochondrial transcription termination factor (MTERF), aquaporin PIP 1-2, protein detoxification 48 (DTX48) and inositol-tetrakisphosphate 1-kinase 2 (ITPK2). These proteins are regulatory proteins involved in the regulation of signal transduction and gene expression that respond to drought stress. The meta-QTLs derived from this study and the genes that have been identified can be used effectively in molecular breeding and in genetic engineering for drought resistance/tolerance in rice.
Droughts are slow-moving natural hazards that gradually spread over large areas and capable of extending to continental scales, leading to severe socio-economic damage. A key challenge is developing accurate drought forecast model and understanding a models' capability to examine different drought characteristics. Traditionally, forecasting techniques have used various time-series approaches and machine learning models. However, the use of deep learning methods have not been tested extensively despite its potential to improve our understanding of drought characteristics. The present study uses a deep learning approach, specifically the Long Short-Term Memory (LSTM) to predict a commonly used drought measure, the Standard Precipitation Evaporation Index (SPEI) at two different time scales (SPEI 1, SPEI 3). The model was compared with other common machine learning method, Random Forests, Artificial Neural Networks and applied over the New South Wales (NSW) region of Australia, using hydro-meteorological variables as predictors. The drought index and predictor data were collected from the Climatic Research Unit (CRU) dataset spanning from 1901 to 2018. We analysed the LSTM forecasted results in terms of several drought characteristics (drought intensity, drought category, or spatial variation) to better understand how drought forecasting was improved. Evaluation of the drought intensity forecasting capabilities of the model were based on three different statistical metrics, Coefficient of Determination (R2), Root Mean Square Error (RMSE), and Mean Absolute Error (MAE). The model achieved R2 value of more than 0.99 for both SPEI 1 and SPEI 3 cases. The variation in drought category forecasted results were studied using a multi-class Receiver Operating Characteristic based Area under Curves (ROC-AUC) approach. The analysis revealed an AUC value of 0.83 and 0.82 for SPEI 1 and SPEI 3 respectively. The spatial variation between observed and forecasted values were analysed for the summer months of 2016-2018. The findings from the study show an improvement relative to machine learning models for a lead time of 1 month in terms of different drought characteristics. The results from this work can be used for drought mitigation purposes and different models need to be tested to further enhance our capabilities.