Search

Climate change and anthropogenic activities have impacts on fish habitat suitability, demanding more accurate modeling of species abundance for effective conservation and management. In this study, we applied Machine Learning techniques to model the habitat-abundance relationship of juvenile Atlantic salmon (Salmo salar) in the Teno catchment in Finland and Norway. To capture the complexity and nonlinearity of the habitat-abundance relationship, we employed Support Vector Regression (SVR), Random Forest (RF), Gradient Boosting (GB), and Support Vector Classification (SVC) and compared their performances. Among the regression models considered, those incorporating input variables such as substrate, shade, and vegetation demonstrate higher performance. Support Vector Regression yields the highest mean cross-validation score (R2 = 0.58), and Gradient Boosting produces the highest test score (R2 = 0.6) among the regression techniques. The mean cross-validation and test scores obtained for the classification models are notably higher compared to the regression models across all scenarios. A comparison between regression and classification results highlights the challenges of accurately modeling the habitat-abundance relationship. This study provides insights into the challenges and potential of machine learning techniques for juvenile Atlantic salmon habitat-abundance modeling in complex riverine habitat environments. The findings emphasize the importance of considering the limitations of machine learning models, particularly in ecological contexts, and the need for further research to address temporal variations and improve the precision of habitat-abundance modeling.

Understanding the impact of Climate Variability (CV) on crop yield is crucial for developing sustainable agriculture practices, especially in regions vulnerable to climate change. This study aims to identify the causes of the observed decline in potato yield in Northern Finland by analyzing Remote Sensing data and statistical analysis on climatic variables from 2001 to 2020. First, the exception years with critical production (2004, 2006, 2008, 2012, 2015) were selected based on the anomaly in the annual potato yield. Then a variety of extreme indices based on precipitation and Land Surface Temperature occurrence and intensity during the growing season were calculated to find how much impact they have on potato yield. Principal Component Analysis was used to select the most significant ones among the extreme indices. Finally, through a multiple regression analysis, we found that extreme precipitation events and cumulative temperature explain around 48 % potato yield variations in which extreme precipitation (with 38 %) had much more impact than cumulative temperature (with 10 %). We concluded that one degree increase in cumulative temperature increases potato yield by 19.64 kg/ha and in contrast, heavy precipitation plays a negative role, i.e., one day increase in extreme precipitation events, decreases potato yield by 2085 kg/ha.

In recent years, the effects of human activities and climate change on river flow patterns have become a major concern worldwide. This is particularly true in the southern Caspian Sea (SCS) region of Iran, where increasing water-intensive socio-economic development and climate change have significantly altered river flow regimes. To better understand these changes, this study employs two nonparametric methods, the modified Mann-Kendall method (MK3) and Innovative Trend Analysis (ITA), to examine spatial and temporal changes in hydrometeorological variables in the SCS. The study also evaluates the impact of human activities and climate change on river flow alteration using elasticity-based methods and the Budyko hypothesis in 40 rivers on the closest gauges to the Caspian Sea. The results indicate an alarming trend of increasing temperature, potential evapotranspiration, and decreasing river flows in the SCS region. In particular, human activities were found to be responsible for around 91.7 % of the change on average, resulting in a significant decline in inflow to the Caspian Sea by about 3216 MCM annually. This declining trend in inflow could potentially exacerbate the eutrophication conditions in the Sea and negatively impact its ecosystem and economics. Therefore, appropriate measures need to be taken to address these environmental and socio-economic issues in the southern Caspian Sea region.

This research study investigates the impact of air temperature and precipitation on annual potato crop yield in Finland region and a local area in northern Finland. For this, the annual crop yield data of regional and local case study area is processed using Z-score normalization technique. Classification of computed z-score values was carried out into different classes ranging between the most beneficial crop yield year and the most vulnerable crop yield year. Later, the detection of feasible potato cropping season at monthly and daily scale was carried out using different weather parameters. Further, long-term trend analysis using Mann-Kendall's approach at annual, seasonal, and monthly scales was carried out using 60 years of dataset of both case study areas. Then after, the comparative analysis of annual crop yield and the characteristics obtained within climate data using different statistical approaches at annual, seasonal, and monthly scale. Finally, multivariate analysis was carried out to find most influential climate variables obtained using different statistical signatures. The results shows that, over the 100 years of period the annual potato crop yield of regional case study area shows a rising trend with declining area under potato crop. Classification approach found 16 % annual yield scored lowest Z-score while, 18% the highest. Likewise, 20 years of data for the local case study area found that 25 % of the dataset scored the highest Z-score and 15 % of the dataset values scored the lowest. Long-term trend analysis of air temperature shows significant increasing trend annually, seasonally and for monthly during the months between July-September. Whereas, similar procedure with the precipitation data showed increasing trend only at annual scale with the precipitation data analysis. During the comparative analysis between the annual crop yield data based on z-score classification and different statistical results obtained from weather parameters such as variation of precipitation and temperature sum, long-term climate data maximum-minimum totals seasonally as well as monthly during crop growing season; noticeable anomalies were observed in the weather parameters in line with the crop yield years grouped into the lowest and the highest Z-scores. The Multivariate analysis emphasized the impact of air temperature over precipitation on potato crop yield. Present study provides quantitative assessment on usefulness of long-term climate signatures for region specific either event-based or crop-based modelling development efforts to provide efficient decision support for enhancing farm-level crop productivity and sustainability of local and regional agriculture.