Odisha State Research Articles

Assessing the impact of ecological, climatic, and socioeconomic factors on age-specific malaria incidence in India: a mixed-model approach using the Global Burden of Disease Study (2010–2019)

BackgroundMalaria continues to be a critical public health concern in India, predominantly driven by complex interplays of ecological, climatic, and socioeconomic factors.MethodsThis study aimed to assess the association between climatic variables (temperature and precipitation) and malaria incidence across India from 2010 to 2019, utilizing data from the Global Historical Weather and Climate Data for climate metrics and the Global Burden of Disease Study for malaria incidence rates. Generalized Linear Mixed Models (GLMMs) with a Poisson distribution were employed to analyze the data, adjusting for socio-economic status, as indexed by the Human Development Index (HDI).ResultsThe results indicated a declining trend in both the number of malaria cases and age-specific incidence rates (ASIR) over the study period. In 2010, India reported approximately 20.7 million cases with an ASIR of 1688.86 per 100,000 population, which significantly reduced to 9.8 million cases and an ASIR of 700.80 by 2019. High malaria incidence was consistently observed in the states of Jharkhand and Odisha, whereas Sikkim reported the lowest numbers. Statistical analysis identified significant associations between malaria incidence and both temperature deviations and precipitation levels, with variations also linked to HDI, suggesting better detection and reporting capabilities in more developed areas.ConclusionThe study underscores the critical interactions between climatic variables and socio-economic factors in shaping the trends of malaria incidence across India. These findings highlight the necessity for adaptive, localized public health strategies that integrate environmental monitoring with socio-economic data to efficiently predict and manage malaria outbreaks.

Staging Statecraft: Dance Festivals and Cultural Representations in Konark, Odisha, India

This essay argues that dance festivals are choreographed spaces that shape cultural heritage. The Konark Dance Festival in Odisha, India, is an annual program situated around the Konark Sun Temple, a UNESCO-recognized World Heritage Site. The following explores the interrelationship between the modern space of the temple monument and the modern format of festival dances in Konark. The festival project juxtaposes the monument’s archaeological value with the dances’ cultural value in choreographic neatness, which requires a critical interrogation to determine the negotiations, appropriations, and discomfort these processes otherwise entail. This article also branches out into cultural discourses beyond the stated festival that examine the historical, diplomatic, and touristic networks the dance festival often encompasses. Following the creation of the modern state of Odisha (in 1936) and of the independent nation of India (in 1947), Odisha regional dance forms were remodelled to produce the state dance Odissi, which gained national “classical” recognition in the 1960s and subsequent international repute. Odissi dance has subsequently been formulated and globally circulated as an anthropomorphic symbol of the geopolitical state of Odisha. Through ethnography, visual study, and choreographic analysis, this essay explores the (re)presentational aspects of the region-state in and through dance, which rhetorically inform the staging of the Konark Dance Festival.

EXPLORING THE ASSOCIATION BETWEEN HOUSEHOLD SANITATION AND WOMEN’S MENSTRUAL HYGIENE MANAGEMENT IN RURAL ODISHA, INDIA

IntroductionAccess to water, sanitation, and hygiene (WASH) facilities has been globally recognized as a critical need, especially for women and girls to ensure their menstrual hygiene. This study aimed to investigate the association between household sanitation and women’s menstrual management experience in Odisha, India. MethodsA cross-sectional study was conducted in Balasore district of Odisha state in India among 694 rural women and girls aged 15-45 years selected using a multi-stage sampling method. The Performance Monitoring and Accountability (PMA) 2020 questionnaire was used for data collection. Multivariate logistic regression analysis was carried out using SPSS version 25. ResultsMore than two-third (68.4%) of rural families used improved sanitary facilities. Around 30% of households have been using an unimproved sanitary facility, which means the practice of open defecation is still prevalent in rural areas. About 40.6% of women and girls reported using clothes as their primary menstrual hygiene material. Further, women and girls with improved sanitation facilities (aOR = 1.56, 95% CI: 1.09 - 2.59) were more likely to change menstrual materials at the main household sanitation facility than those with an unimproved sanitation facility. In contrast, households using improved sanitation facility were less likely to use bedroom/sleeping areas to change the menstrual materials (aOR=0.65, 95% CI: 0.42-0.99) than those with an unimproved facility. ConclusionAvailability of improved household sanitation is critical to good menstruation management practices. State-specific policy for menstrual health and hygiene could provide the much-needed impetus to strengthen WASH infrastructure in rural and tribal regions of Odisha.

Agricultural drought monitoring and early warning at the regional scale using a remote sensing-based combined index.

Early detection of agricultural drought can alert farmers and authorities, enhancing the resilience of the food sector. A framework is proposed for developing a novel regional agricultural drought index (RegCDI) by combining remotely sensed vegetation health, soil moisture and crop water stress via a transparent Shannon's entropy weighting method. The framework consists of the selection of suitable datasets based on their regional performance, the aggregation of selected drought indicators, the validation of the combined index against crop yield, and the testing of predictive capabilities. The creation and performance of RegCDI are demonstrated for the drought prone Indian state of Odisha. MODIS surface reflectance is selected for crop water stress and GLDAS-2 for assessing soil moisture deficits and vegetation health. Three selected indicators (SMCI, TCI, and SIWSI-1) are combined into RegCDI for Odisha. The performance of RegCDI is evaluated (a) against other popular drought indices and (b) by comparing with seasonal crop yields. RegCDI is used to identify drought hotspots based on drought severity, duration, and propensity over the study area. A reforecast evaluation of RegCDI (up to three months ahead) showed that the indicators based on soil moisture deficit and crop water stress could predict drought conditions up to two months ahead with no less than 80% accuracy. This demonstrated the potential of the RegCDI framework and its component indicators for early warning of drought in Odisha.

Insights into human-wildlife interactions and community views on mangrove restoration in Kendrapada District, Odisha, India

This paper evaluates interactions between humans, Wild Boars, and crocodiles in mangrove ecosystems of the villages of Benakanda, Bhateni, and South Jambu in Mahakalapada Block in the Kendrapada District of the Indian state of Odisha, using questionnaire surveys. This is an area where mangrove restoration is currently in progress. Using a targeted sampling procedure, 280 respondents representing 14% of the population participated in the study. The results show that negative perceptions differ throughout villages, with a majority of respondents reporting interaction between humans and animals in Bhateni (91%) and South Jambu (98%). The most frequent animal reported to cause harm to crop and livelihoods is Wild Boar (44%). Communities understand the value of mangrove restoration despite facing obstacles brought on by interactions with wildlife. The vast majority of residents (87%) believe that restoration efforts were necessary, and many had taken part in these by themselves, or in conjunction with other communities.

Health System Resilience and Sustainability in India - Odisha's Strategies on Human Resources Management during COVID-19

Background: COVID-19 pandemic caused widespread loss of life, economic downturns, emotional distress and overwhelmed the public health delivery systems across the globe. Odisha was one of the few states in India that deployed proactive management of human resources in health (HRH) to fight the menace. This paper analyzes key decisions related to HRH during COVID-19. The findings aim to strengthen HRH practices to address future pandemics. Materials and Methods: We analyzed the structures, functions, and processes related to HRH management during the COVID-19, using a qualitative lens. Through purposive sampling, in-depth interviews were conducted with 20 key informants, including policymakers and state-level managers. Data were analyzed thematically to reflect upon the perspectives of key stakeholders, identify barriers and enablers, and document the decision-making dynamics. Results: Odisha strengthened its hospital infrastructure and capacity of health workforce through additional deployment and skill upgradation in a short period. Restriction of movements and strengthening the health system pillars led to considerable success. As COVID-19 cases surged in mid-2020, focus shifted to clinical treatment, active case finding and surveillance. Specific training modules were developed with guidance from the Ministry of Health, WHO, and UNICEF. A whole range of human resources were trained by both online and offline modes. Community-level training programs focused on enforcing COVID-appropriate behavior and management of vulnerable population. Infusion of technology enhanced the system’s capacity to deliver high quality training in a short period of time to a vast majority of stakeholders. Conclusion: The Odisha State Disaster Management Authority (OSDMA) and the National Health Mission (NHM) played critical roles in enhancing systems’ preparedness and institutionalizing such large-scale capacity building initiatives during periods of crisis. The state's approach in terms of scale, skill, and speed of human resources management could be a model for addressing future health crises.

Geo-Hydrobiology and Geoinformatics Mapping of Ethnobotany in the Gandhamardan Hills, Odisha, India

Objective: The Gandhamardan Hills (GMH)range is a group of small mountains in Peninsular India in Balangir district in Odisha state in India. There is uniqueness in geology, geography, geomorphology, climatology, Hydrology, petrology, and lithology. The lithology, soil, water, geomorphology, and traditional use of plants in Ayurveda (India) have holistic medicinal/surgery. origin. Geo-hydro-biological amalgamation through Geological Information Systems (GIS) and chemical analysis is still being explored, and the present research emphasises such studies. Methods: Data about geo-hydro-biology through grapy, geology, geomorphology, hydrology, and traditional medicinal practices are implored from literature sources, using TOPO and Q-GIS maps and ERDAS software; their analytical interpretations were reported. The chemical analysis was conducted using X-ray fluorescence spectrometric studies of the water and soil of GMH, and the exuberance of ethnobotanical species in GMH was correlated. Results Laboratory analysis, literature studies, and interaction with Ayurvedic and Kaviraj practitioners, 154 popular species databases with their pharmacological applications reported for ordinary people. Many species have multidimensional applications that can transform Ayurveda into Materia medica. Conclusion: This ethnobotanical study documented the use of plants by the local community. The natural medicinal plants are cheap for the rural communities. The information gathered can be used for further scientific investigation to develop new commercial plant-based medicines as they will be safer than synthetic drugs. SDGs 1 to 3 and 12, 13, and 15 will be satisfied if we can conserve and adequately manage the hub of medicinal plants in GMH.

Odissi on Screen: A Meditation on Regional Television

This article aims to interrogate the role of the television screen in creating, re-creating, disseminating, and deconstructing the dancing body. It presents a study of the contemporary landscape of odissi dance, a nationally recognized Indian traditional art form from the eastern Indian state of Odisha, through its on-screen representation. As an odissi soloist, I register, analyze, and interpret screenic data, mainly televised interviews of dancers, live telecasts of dance festivals in Odisha, and performances recorded for the camera in the studios. I focus on content primarily broadcast on the state-owned satellite channel broadcasting in Odia, the official language in Odisha. My position is of a Sahrdaya, an observer tutored in the codes and conventions of the art form and critically responsive to the structure of emotion in the presentation. I locate the dancing body across discursive, disseminative, and choreographic renditions. This subjective positioning, I argue, democratizes the expressive ethos of odissi embodiment. Commenting on the contemporary curation of the dancing body by the state network, this essay brings larger questions around the representation of gender, sexuality, caste, and regionalism on the television screen.

Civil society, local government and rural health in an eastern Indian state

ABSTRACT This paper explores how civil society mobilization makes a difference in local government performance in delivering rural healthcare. The study was carried out during 2019–2020 in tribal-dominated Nilgiri and Daringbadi blocks of Odisha state in eastern India. Civil society activism is found to interject more programmatic priorities into local governance of health in Nilgiri than in Daringbadi. Success in Nilgiri is linked to its history of subaltern mobilization, the organizational efforts of a pro-poor political party and a comparatively mobilized civil society. Conversely, failure in Daringbadi is linked to a fractured community, little if any history of civil society mobilization and hegemony of the ruling party which uses local government to advance its own political agenda.

Understanding addictive behaviour of a group of slum dwelling female SLT users on the basis of PRIME theory: A case study in Odisha, India

ABSTRACT Context: Tobacco addiction is an important public health problem. Among several theories of addiction proposed, PRIME theory of motivation is found to be a comprehensive one to synthesise prevention strategies. Aims: This case study was conducted on the basis of PRIME theory to explain smokeless tobacco (SLT) addiction patterns among slum dwelling female residents of Cuttack district, Odisha. Settings and Design: Cuttack district of Odisha state and Qualitative synthesis. Methods and Material: Qualitative semistructured face-to-face interviews and framework analysis techniques were employed. The study was conducted over a period of 2 months between February 2020 and March 2020. Face-to-face interviews of 26 participants of Dasha Sahi slum using a semistructured questionnaire assessing responses based on five main themes including P, Plans; R, Responses; I, Impulses And Inhibitory Forces; M, Motives; and E, Evaluations of the said theory. Statistical Analysis Used: Verbatim transcripts were analysed using thematic framework analysis. Results: A majority of the participants were multiple SLT product users, and they did not have an immediate plan to quit. Most of the participants showed strong emotional attachment with these products and considered them the only source of pleasure (want) in a life full of miseries. The words “Tobacco” and “Nicotine” were medical jargons for them. Though they were aware of the harmful effects, they had a positive evaluative belief about its use because of cognitive dissonance. Most of them were habitual users living in an environment full of physical and social cues. Conclusions: This case study is well in line with the PRIME theory in explaining the addictive behaviour; a comprehensive multi-strategic approach was formulated for inculcating quitting behaviour among this disadvantaged section of the population as suggested by the proposer of this theory.

Geospatial fish consumption patterns and paradigmsin Odisha State, India

The current study investigated the geographic distribution and characteristics of fish consumption in Odisha State, India. The study was conducted across various locations, comprising urban coastal (Puri), rural coastal (Balasore), urban non-coastal (Cuttack) andrural non-coastal (Mayurbhanj) districts in the state. A total of 1440 respondents were selected for assessing the fish consumption patterns across theses diverse locations. According to the consumer profile, 82% of respondents were between the age of 20 and50, with 24% having a college degree. More than 90% of the respondents reported that they consume fish regularly. The results indicated that increased fish availability (62%), accessibility (52%), and affordability (48%) contributed to a rise in fish consumption over time. Over all, distance to the fish access points ranged between 1 to 2 . Catla was the most preferred fish species among consumers, followed by Rohu and other carps. Several barriers to increasing fish consumption were identified based on the perceptions of the respondents, such as erratic availability, lack of preference for fresh fish, wide price variations, limited access and high price. The data were analysed using a range of statistical and econometric methods, including conjoint analysis, preference assessment index and discriminant analysis. Keywords: Coastal, Conjoint analysis, Discriminant analysis, Fish consumption, Non-coastal, Preference assessment index

The Kudmi (Kudumi), a totemic community of Jharkhand State and near about parts (India) – critical evaluation for inclusion in ST category

The Kudmi (Kudumi) a totemic primitive community (tribe) originated and evolved from the Neanderthal man (Homo Sapiens neanderthdemais) 2,30,000 years ago, like all other human beings, which is evidenced by the evolutionary theories based on fossil findings and population genetics. They are inhabiting in the state of Jharkhand and its near about, i.e. of West Bengal, Assam, Odisha and Chattisgarh states since time immemorial, who were classified as “Primitive tribes” by the British regime in India in 1865, alongwith other primitive tribes under the term of the Indian succession Act, as they have customary rules of sucession. Subsequently in 1913 and 1931 they were included in the list of tribes (Primitive Tribes). But unfortunately, they were omitted as from the ST category drawn up in 1950 for reasons that are unknown, although they are having traits of Primitive Tribes, e.g., they are totemic (alike all other primitive tribes of India and the world) i.e. their lineage related to plants, animals and other natural objects, shyness of contact with other communities at large, distinctive culture, geographically isolated, Backwardness (towards past, keeping back and slow is learning) and specific mother tongue-“Kudmali’.Under the above circumstances the Kudmis of the above noted geographical area be again reincluded in the ST category by the present authority concerned to bring them to the main stream of development of the country and to uplift their life style and social status at large.

Effect of a behavior change and hardware intervention on safe child feces management practices in rural Odisha, India: a cluster-randomized controlled trial

BackgroundPoor child feces management contributes to enteropathogen exposure and, consequently, is associated with diarrheal disease and negative impacts on child growth. Despite high latrine coverage, only 37% of Indian households safely dispose of their child’s feces into a latrine or have the child use the latrine, with the lowest rate in the state of Odisha at 12%. We evaluated a behavior change and hardware intervention designed to improve caregiver safe disposal of child feces and child latrine use.MethodsWe conducted a cluster-randomized controlled trial among 74 villages in rural Odisha, India. Eligible villages previously participated in a water and sanitation infrastructure program. Following a baseline survey, half the villages were assigned to intervention and half to control. Caregivers of children < 5 years old from households with a latrine were eligible to participate. The intervention included five behavior change activities. Hardware was provided at the first activity, based on child age, to aid safe disposal and latrine training (wash basin and bucket with lid for children < 7 months old; latrine training mat platform with removable tray for children 7 to 48 months old). The primary outcome was caregiver reported ‘safe disposal’ as defined by the WHO/UNICEF Joint Monitoring Programme (JMP) which encompasses two behaviors: caregiver disposal of child’s feces into a latrine and child latrine use. Safe disposal was measured four to six months after intervention delivery (endline).ResultsEndline analysis included 665 intervention caregivers (840 children) and 634 control caregivers (785 children). Prevalence of JMP-defined safe disposal was 1.16 times greater in the intervention arm compared to control (77.7% vs. 65.9%; prevalence ratio [PR] 1.16, 95% CI 1.04–1.29), with higher prevalence of caregiver safe disposal (18.6% vs. 13.6%; PR 1.46, 95% CI 1.12–1.92) but no significant difference in child latrine use (59.0% vs. 52.2%; PR 1.06, 95% CI 0.95–1.18). When restricted to children < 3 years old, JMP-defined safe disposal was 1.42 times greater (67.5% vs. 46.7%; PR 1.42 95% CI 1.21–1.67) with higher prevalence of both caregiver safe disposal (34.6% vs. 25.7%; PR 1.44, 95% CI 1.11–1.86) and child latrine use (32.9% vs. 20.9%; PR 1.41, 95% CI 1.08–1.83).ConclusionsThe intervention increased JMP-defined safe disposal, with substantial improvements in both caregiver safe disposal and child latrine use among children < 3 years old. While future research is needed to demonstrate sustainability of these effects, our results suggest a potentially scalable intervention for improving child feces disposal and reducing disease.Trial registrationThis trial was retrospectively registered at ISRCTN15831099 on 18/02/2020, which was approximately two months after the first participant was recruited for the baseline survey on 02/12/2019.

Evaluation of leaching parameters for dissolving Ni and Co from chromite overburden using acidophilic bacterial consortium

ABSTRACT The chromite mine of Sukinda Valley located in the Indian state Odisha produces a large amount of overburden during the mining of chromite ore. The overburden waste contains different valuable metals with very low concentrations. Its environmental metal leaching contaminates nearby water resources, which creates serious chaos in the local communities. However, the presence of Ni-oxide in the overburden makes it the only Ni resources of India. Therefore, an experimental attempt was made to evaluate the possibility of Ni recovery from the overburden. The physico-chemical analysis of the overburden sample showed that it contains 0.89 and 0.031% (w/w) of Ni and Co, respectively, which remain embedded within the goethite matrix. Bioleaching may be suitably applied to it. Therefore, bioleaching of Ni and Co from the overburden sample was conducted using an acidophilic bacterial consortium. Effect of leaching parameters like contact time, initial pH, temperature, Fe(II) addition, and pulp density was evaluated. Bioleaching of the overburden sample using the acidophiles was found to be effective. Further, all the leaching parameters showed positive effect on the bioleaching efficiency.

Empirical evaluation of agricultural resilience to climate change: an application to the Indian state of Odisha

Empirical evaluation of agricultural resilience to climate change: an application to the Indian state of Odisha

Rural local government and healthcare delivery in an Eastern Indian state

Based on field research in the remote and tribal-dominated Kandhamal district in the eastern Indian state of Odisha during 2019-20, the study examines the extent to which Constitutionally-created rural self-governance institutions (village Panchayats) fulfilled their mandated healthcare functions. Primary data was collected from villagers, front-line public health officials, elected local government (Panchayat) members and party cadres through focus group discussions and interviews. Employing the Foucauldian governmentality framework, the analysis moves away from a depoliticized understanding of decentralized delivery of rural health. The study concludes that Panchayats’ contributions to rural health are influenced by politically motivated factors, which may not be compatible with considerations of democracy and efficiency. Panchayat performance in the study villages remained poor as the state allowed them only regulated freedom and did not create space for their autonomy to flourish. Rural health decentralization led to new forms of governmentality as Panchayats were instrumentally used to consolidate state power at the rural grassroots. Top-down management of political process in these areas makes local government mechanical outpost of the ruling party.

UNDERSTANDING THE GOVERNMENTS SCHEMES DESIGNED FOR TRIBAL WOMENS FINANCIAL INCLUSION IN THE STATE OF JHARKHAND AND ODISHA

Financial inclusion is a vital component for socio-economic development, especially for marginalized communities like tribal women in India. This research article examines the various government schemes aimed at fostering financial inclusion for tribal women in the states of Jharkhand and Odisha. By analysing these initiatives, the study aims to highlight their impacts, challenges, and the way forward for improving financial inclusivity. This detailed analysis is supported by a review of relevant literature and official documents.

A Decision Support System for Crop Recommendation Using Machine Learning Classification Algorithms

Today, crop suggestions and necessary guidance have become a regular need for a farmer. Farmers generally depend on their local agriculture officers regarding this, and it may be difficult to obtain the right guidance at the right time. Nowadays, crop datasets are available on different websites in the agriculture sector, and they play a crucial role in suggesting suitable crops. So, a decision support system that analyzes the crop dataset using machine learning techniques can assist farmers in making better choices regarding crop selections. The main objective of this research is to provide quick guidance to farmers with more accurate and effective crop recommendations by utilizing machine learning methods, global positioning system coordinates, and crop cloud data. Here, the recommendation can be more personalized, which enables the farmers to predict crops in their specific geographical context, taking into account factors like climate, soil composition, water availability, and local conditions. In this regard, an existing historical crop dataset that contains the state, district, year, area-wise production rate, crop name, and season was collected for 246,091 sample records from the Dataworld website, which holds data on 37 different crops from different areas of India. Also, for better analysis, a dataset was collected from the agriculture offices of the Rayagada, Koraput, and Gajapati districts in Odisha state, India. Both of these datasets were combined and stored using a Firebase cloud service. Thirteen different machine learning algorithms have been applied to the dataset to identify dependencies within the data. To facilitate this process, an Android application was developed using Android Studio (Electric Eel | 2023.1.1) Emulator (Version 32.1.14), Software Development Kit (SDK, Android SDK 33), and Tools. A model has been proposed that implements the SMOTE (Synthetic Minority Oversampling Technique) to balance the dataset, and then it allows for the implementation of 13 different classifiers, such as logistic regression, decision tree (DT), K-Nearest Neighbor (KNN), SVC (Support Vector Classifier), random forest (RF), Gradient Boost (GB), Bagged Tree, extreme gradient boosting (XGB classifier), Ada Boost Classifier, Cat Boost, HGB (Histogram-based Gradient Boosting), SGDC (Stochastic Gradient Descent), and MNB (Multinomial Naive Bayes) on the cloud dataset. It is observed that the performance of the SGDC method is 1.00 in accuracy, precision, recall, F1-score, and ROC AUC (Receiver Operating Characteristics–Area Under the Curve) and is 0.91 in sensitivity and 0.54 in specificity after applying the SMOTE. Overall, SGDC has a better performance compared to all other classifiers implemented in the predictions.

Predicting forest fire probability in Similipal Biosphere Reserve (India) using Sentinel-2 MSI data and machine learning

The global escalation in forest fires, characterized by increasing frequency and severity, results from a complex interplay of natural and anthropogenic factors, exacerbated by climate change. These fires devastate habitats, threaten species, reduce biodiversity, disrupt natural cycles, and harm local ecosystems. The impacts are particularly damaging in biological reserves. The Similipal Biosphere Reserve (SBR) in Odisha State is one of India’s major forest fire hotspots, experiencing forest fires almost every year. The objective of this study is to develop a predictive model using Sentinel-2 MSI data and machine learning (ML) techniques to estimate the probability of forest fires in the SBR, India, thereby enhancing disaster management and prevention in the region. This research maps and quantifies forest fire intensity by leveraging ML algorithms, namely Extreme Gradient Boosting (XGBoost), Gradient Boosting Machine (GBM), Support Vector Machine (SVM), and Random Forest (RF). To develop a Forest Fire Probability (FFP) map, twenty conditioning factors, along with pre- and post-fire Normalized Burn Ratio (NBR) and delta Normalized Burn Ratio (dNBR), were utilized. Furthermore, four statistical methods—Mean Absolute Error, Mean Square Error, Root Mean Square Error, and Overall Accuracy—were employed to analyze the FFP. The results were validated using the Area Under Curve (AUC) method. The analysis identifies 2021 as the year with the highest incidence of forest fires, accounting for 29.19% of the occurrences. Among the models, the GBM exhibits superior performance, highlighting its efficacy in handling large, multidimensional datasets. Predictive mapping suggests that approximately 1400–1500 km2, or 25–30% of the studied area, faces a high to very high risk of forest fires.

Streamflow prediction model for agriculture dominated tropical watershed using machine learning and hierarchical predictor selection algorithms

Study regionRana watershed, located in the mid-Mahanadi River basin in the state of Odisha, India. Study focusThis study attempted to develop a generalizable machine learning (ML)-based streamflow prediction model implementing prediction selection algorithms to the physiographic characteristics, and hydro-meteorological data collected for Rana Watershed. New hydrological insightsThe pertinent predictors identified were land use/ land cover (LULC), one and two-day lagged rainfall, one-day lagged PET, and one-day lagged streamflow and its categorized flow regime. The random forest algorithm, which outperformed the other five algorithms evaluated, was trained using identified predictors to develop a streamflow prediction model called “stRFlow”. The mean absolute error, root mean squared error, coefficient of determination, and Nash-Sutcliffe efficiency during training were 0.753 m3/s, 3.584 m3/s, 0.973, and 0.972 and testing were 2.829 m3/s, 10.503 m3/s, 0.855, and 0.851, respectively. The Kling-Gupta efficiency was found to be 0.96 and 0.92 during training and testing, respectively. There was an enhancement to model proficiency with the addition of LULC to temporal predictors. Moreover, the partial auto-correlation factor for the streamflow and examining the categorization of specific lagged flow regimes enhanced the predictive capacities of “stRFlow”. Results depict the potential of stRFlow and the framework in streamflow modeling in similar hydroclimatic regions with applicability for practical and reliable streamflow predictions globally.