Subsidence, erosion, and degradation in agricultural peatlands are leading to the disappearance of highly fertile farmland. This study investigated two strategies aimed at extending the lifespan of cultivated peat soils: the application of straw and wood chips to compensate for soil losses and the application of copper (Cu) to slow peat decomposition, based on previous recommendations. Peat soil samples (270 g) were amended with 11 t ha ^–1 of biomass materials (14.8 g kg ^–1 ) and 235.6 mg Cu kg ^–1 and incubated in glass jars at constant temperature and water content. Thirty chemical parameters were then monitored over a 56‐d period through repeated soil sampling. Discriminant analysis showed that the addition of biomass had the greatest affect on nitrogen (N) availability, immobilizing 7.8 to 12.1 kg of inorganic N per metric ton of incorporated biomass. Considering that peat soils may require from 4 to 40 t biomass ha ^–1 yr ^–1 to reach carbon equilibrium, the tested biomass materials could immobilize from 34 to 500 kg ha ^–1 of N if confirmed at the field scale. This may help capture excess N but may also limit crop growth. Alternatively, slowing decomposition could reduce both biomass requirements and N immobilization. However, the results show that Cu had little effect on parameters linked to organic matter decomposition. Indeed, dissolved organic carbon was decreased by 11% in Cu‐treated soils. A longer‐term study should be conducted to confirm these observations at the field scale, thus helping to develop conservation strategies suitable for agricultural production.

In the current study, a new hybrid machine learning (ML)-based model was developed by integrating a convolution neural network (CNN) with a random forest (RF) to forecast pesticide use on golf courses in Québec, Canada. Three main groups of independent variables were used to estimate pesticide use on golf courses, expressed as actual active ingredient rate (AAIR): (i) coordinates (i.e., longitude and latitude of the golf course), (ii) characteristics of the golf courses (i.e., pesticide type and the number of holes), and (iii) meteorological variables (i.e., total precipitation, P, and average temperature, T). The meteorological variables were collected from the Google Earth Engine by developing a JavaScript-based Code. On the basis of the different periods of total precipitation and average temperature, four different scenarios were defined. A data bank with more than 40,000 samples was used to calibrate and validate the developed model such that 70% of all samples were randomly selected to calibrate the model, while the remainder of the samples (i.e., 30%) that did not have any role in calibration were employed to validate the model’s generalizability. A comparison of different scenarios indicated that the model that considered the longitude and latitude of the golf course, pesticide type, and the number of holes in golf courses as well as total precipitation and average temperature from May to November as inputs (R = 0.997; NSE = 0.997; RMSE = 0.046; MAE = 0.026; NRMSE = 0.454; and PBIAS (%) = −0.443) outperformed the other models. Moreover, the sensitivity analysis result indicated that the total precipitation was the most critical variable in AAIR forecasting, while the average temperature, pesticide types, and the number of holes were ranked second to fourth, respectively.

Golf course maintenance requires the use of several inputs, such as pesticides and fertilizers, that can be harmful to human health or the environment. Understanding the factors associated with pesticide use on golf courses may help golf-course managers reduce their reliance on these products. In this study, we used a database of about 14,000 pesticide applications in the province of Québec, Canada, to develop a novel hybrid machine learning approach to predict pesticide use on golf courses. We created this proposed model, called RF-SVM-GOA, by coupling a support vector machine (SVM) with random forest (RF) and the grasshopper optimization algorithm (GOA). We applied RF to handle the wide range of datasets and GOA to find the optimal SVM settings. We considered five different dependent variables—region, golf course ID, number of holes, year, and treated area—as input variables. The experimental results confirmed that the developed hybrid RF-SVM-GOA approach was able to estimate the active ingredient total (AIT) with a high level of accuracy (R = 0.99; MAE = 0.84; RMSE = 0.84; NRMSE = 0.04). We compared the results produced by the developed RF-SVM-GOA model with those of four tree-based techniques including M5P, random tree, reduced error pruning tree (REP tree), and RF, as well as with those of two non-tree-based techniques including the generalized structure of group method of data handling (GSGMDH) and evolutionary polynomial regression (EPR). The computational results showed that the accuracy of the proposed RF-SVM-GOA approach was higher, outperforming the other methods. We analyzed sensitivity to find the most effective variables in AIT forecasting. The results indicated that the treated area is the most effective variable in AIT forecasting. The results of the current study provide a method for increasing the sustainability of golf course management.

The accelerating impact of climate change on golf course conditions has led to a significant increase in pesticide dependency, underscoring the importance of innovative management strategies. The shift from Coupled Model Intercomparison Project Phase 5 (CMIP5) to the latest CMIP6 phase has drawn the attention of professionals, including engineers, decision makers, and golf course managers. This study evaluates how climate projections from CMIP6, using Canadian Earth System Models (CanESM2 and CanESM5), impact pesticide application trends on Quebec’s golf courses. Through the comparison of temperature and precipitation projections, it was found that a more substantial decline in precipitation is exhibited by CanESM2 compared to CanESM5, while the latter projects higher temperature increases. A comparison between historical and projected pesticide use revealed that, in most scenarios and projected periods, the projected pesticide use was substantially higher, surpassing past usage levels. Additionally, in comparing the two climate change models, CanESM2 consistently projected higher pesticide use across various scenarios and projected periods, except for RCP2.6, which was 27% lower than SSP1-2.6 in the second projected period (PP2). For all commonly used pesticides, the projected usage levels in every projected period, according to climate change models, surpass historical levels. When comparing the two climate models, CanESM5 consistently forecasted greater pesticide use for fungicides, with a difference ranging from 65% to 222%, and for herbicides, with a difference ranging from 114% to 247%, across all projected periods. In contrast, insecticides, growth regulators, and rodenticides displayed higher AAIR values in CanESM2 during PP1 and PP3, showing a difference of 28% to 35.6%. However, CanESM5 again projected higher values in PP2, with a difference of 1.5% to 14%.