Search

Incorporating cover crops into the rotation is a practice applied across many parts of the globe to enhance soil biological activities. In dryland farming, where crop production is highly dependent on rainfall and soil water storage, cover cropping can affect soil water, yet its effects on soil hydrological and biological health require further investigation. The objective of this study was to evaluate the effect of different timing of summer sorghum cover crop termination on soil water, total and labile organic carbon, arbuscular mycorrhizal fungi and their mediating effects on wheat yield. Through on-farm trial, soil characteristics along with wheat biomass, yield and grain quality were monitored. In comparison with the control (fallow), the early terminated cover crop was the most effective at retaining greater soil water at wheat sowing by 1~4% in 0–45cm soil profile. An increase in water use efficiency, yield and grain protein by 10%, 12% and 5% was observed under early termination. Under late terminated summer cover crop, there was 7% soil water depletion at wheat planting which resulted in 61% decline in yield. However, late-terminated cover crop achieved the greatest gain in soil total and particulate organic carbon by 17% and 72% and arbuscular mycorrhizal fungal Group A and B concentration by 356% and 251%. Summer cover crop incorporation resulted in a rapid gain in labile organic carbon, which constituted hotspots for arbuscular mycorrhizal fungi growth, conversely, fungal activities increased labile organic carbon availability. The combined effect of increased soil water at sowing and over the growing season, organic carbon, and microbial activities contributed to greater yield. The findings suggest that summer cover cropping with timely termination can have implications in managing soil water at sowing time and enhancing soil water storage during the season, soil carbon, and facilitating microbial activities while enhancing productivity in the dryland cropping system. [ABSTRACT FROM AUTHOR]

This paper aims to test different methods used for assessing sediment yield indices to identify hotspots and rank sediment yield hotspots. This process includes the assessment of the entropy weighting (EW), fractal dimension (FD), slope length gradient (SL), and sediment connectivity (SC) methods. The indices at different sub-catchment levels were applied in the Ilanlu catchment (Iran) and organized based on five sediment hazard classes. To assess the performance of sediment hazard mapping, a method of superimposition was used and assessed with the erosion potential model (EPM). The superimposition showed that 8, 10, 4 and 9 sub-catchments, based on the degree of susceptibility, obtained the highest results from FD, EW, SL and SC, respectively, compared with the EPM model. The results show that EW and SC methods can achieve greater performance than FD and SL in identifying sediment production hotspots. [ABSTRACT FROM AUTHOR]

Mixed crop-livestock farming systems provide food for more than half of the world's population. These agricultural systems are predicted to be vulnerable to climate change and therefore require transformative adaptations. In collaboration with farmers in the wheatbelt of Western Australia (WA), a range of systemic and transformative adaptation options, e.g. land use change, were designed for the modelled climate change projected to occur in 2030 (0.4–1.4° increase in mean temperature). The effectiveness of the adaptation options was evaluated using coupled crop and livestock biophysical models within an economic and environmental framework at both the enterprise and farm scales. The relative changes in economic return and environmental variables in 2030 are presented in comparison with a baseline period (1970–2010). The analysis was performed on representative farm systems across a rainfall transect. Under the impact of projected climate change, the economic returns of the current farms without adaptation declined by between 2 and 47%, with a few exceptions where profit increased by up to 4%. When the adaptations were applied for 2030, profit increased at the high rainfall site in the range between 78 and 81% through a 25% increase in the size of livestock enterprise and adjustment in sowing dates, but such profit increases were associated with 6–10% increase in greenhouse gas (GHG) emissions. At the medium rainfall site, a 100% increase in stocking rate resulted in 5% growth in profit but with a 61–71% increase in GHG emissions and the increased likelihood of soil degradation. At the relatively low rainfall site, a 75% increase in livestock when associated with changes in crop management resulted in greater profitability and a smaller risk of soil erosion. This research identified that a shift toward a greater livestock enterprises (stocking rate and pasture area) could be a profitable and low-risk approach and may have most relevance in years with extremely low rainfall. If transformative adaptations are adopted then there will be an increased requirement for an emissions control policy due to livestock GHG emissions, while there would be also need for soil conservation strategies to be implemented during dry periods. The adoption rate analysis with producers suggests there would be a greater adoption rate for less intensified adaptations even if they are transformative. Overall the current systems would be more resilient with the adaptations, but there may be challenges in terms of environmental sustainability and in particular with soil conservation. [ABSTRACT FROM AUTHOR]

Transfer of processed data and parameters to ungauged catchments from the most similar gauged counterpart is a common technique in water quality modelling. But catchment similarities for Dissolved Inorganic Nitrogen (DIN) are ill posed, which affects the predictive capability of models reliant on such methods for simulating DIN. Spatial data proxies to classify catchments for most similar DIN responses are a demonstrated solution, yet their applicability to ungauged catchments is unexplored. We adopted a neural network pattern recognition model (ANN-PR) and explainable artificial intelligence approach (SHAP-XAI) to match all ungauged catchments that flow to the Great Barrier Reef to gauged ones based on proxy spatial data. Catchment match suitability was verified using a neural network water quality (ANN-WQ) simulator trained on gauged catchment datasets, tested by simulating DIN for matched catchments in unsupervised learning scenarios. We show that discriminating training data to DIN regime benefits ANN-WQ simulation performance in unsupervised scenarios (p< 0.05). This phenomenon demonstrates that proxy spatial data is a useful tool to classify catchments with similar DIN regimes. Catchments lacking similarity with gauged ones are identified as priority monitoring areas to gain observed data for all DIN regimes in catchments that flow to the Great Barrier Reef, Australia. [ABSTRACT FROM AUTHOR]

Transfer of processed data and parameters to ungauged catchments from the most similar gauged counterpart is a common technique in water quality modelling. But catchment similarities for Dissolved Inorganic Nitrogen (DIN) are ill posed, which affects the predictive capability of models reliant on such methods for simulating DIN. Spatial data proxies to classify catchments for most similar DIN responses are a demonstrated solution, yet their applicability to ungauged catchments is unexplored. We adopted a neural network pattern recognition model (ANN-PR) and explainable artificial intelligence approach (SHAP-XAI) to match all ungauged catchments that flow to the Great Barrier Reef to gauged ones based on proxy spatial data. Catchment match suitability was verified using a neural network water quality (ANN-WQ) simulator trained on gauged catchment datasets, tested by simulating DIN for matched catchments in unsupervised learning scenarios. We show that discriminating training data to DIN regime benefits ANN-WQ simulation performance in unsupervised scenarios (p< 0.05). This phenomenon demonstrates that proxy spatial data is a useful tool to classify catchments with similar DIN regimes. Catchments lacking similarity with gauged ones are identified as priority monitoring areas to gain observed data for all DIN regimes in catchments that flow to the Great Barrier Reef, Australia. [ABSTRACT FROM AUTHOR]

The state of Western Australia is a major producer and exporter of crops and livestock. Mixed farming systems are typical agricultural enterprises in the Western Australian wheatbelt where climate drives the productivity and profitability of these farms and therefore the effects of likely climate change on their performance need to be understood. Here the effects of climate change projected at 2030 were evaluated compared to a baseline period (1980–1999) on mixed farming systems at paddock, enterprise and whole farm scales using the coupled APSIM and GRAZPLAN biophysical simulation models. The yield of different crops, livestock production and gross margins were assessed under current and projected climates using current farming technology and management practices. Representative mixed-farm systems were selected along a climate transect. Modelling analysis suggests that current production levels and gross margins of mixed farm systems in Western Australia will not be sustained in 2030 climate conditions except in areas of moderately high-rainfall. Whole farm gross margin declined at all site × potential climate scenarios between 1% and 22% except in moderately high rainfall where gross margin increased by up to 4% under a ‘hot and moderate change in rainfall’ climate. Projected crop yields declined for most of the crop × site × potential climate combinations, with greatest declines under a hot and dry climate (at driest margin of transect) in which wheat, barley, canola, and lupin yield declined up to 16%, 15%, 21%, and 27%, respectively. Increase in yield was predicted for wheat and barley at some of the site × potential climate s. Wheat yield increased only under moderately high rainfall region by 6% while barley increased by 1%. Simulated cropping gross margin was also shown to decline by between > 1% and 23%, except for the moderately high-rainfall site where cropping gross margins were projected to increase by up to 3%. Changes in simulated livestock production were smaller and less variable than for crop production. The change in weight of livestock sold across sites × potential climate combinations ranged between − 3% and + 3%. Livestock gross margin varied between − 11% and + 6%. Modelling results indicated a greater fertilisation effect of the elevated CO 2 on pasture production than on crop yield and biomass particularly in drier sites. But however, this could not offset negative impact of climate change under hot potential climates. The main negative environmental impacts from the projected climate change were declines in annual net primary production (ANPP), ground cover and water use efficiency mostly at drier sites. Whole farm N 2 O emission declined significantly for the majority of site × potential climate combinations, while smaller decreases in ruminant CH 4 emission were predicted. In 2030, returns from livestock enterprises are predicted to be smaller, but less variable than from cropping and with increasing probability of success in drier regions. Reduced variability in financial return is important from the perspective of whole farm risk management. Shifts in enterprise mix in dryland mixed-farming systems towards increased livestock may be a helpful strategy in adapting to climate change and managing the associated financial risks. [ABSTRACT FROM AUTHOR]

Wheat is one of the main grains produced across the globe and wheat yields are sensitive to changes in climate. Australia is a major exporter of wheat, and variations in its national production influence trade supplies and global markets. We evaluated the effect of climate change in 2030 compared to a baseline period (1980–1999) by upscaling from farm to the national level. Wheat yields and gross margins under current and projected climates were assessed using current technology and management practices and then compared with ‘best adapted’ yield achieved by adjustments to planting date, nitrogen fertilizer, and available cultivars for each region. For the baseline climate (1980–1999), there was a potential yield gap modelled as optimized adaptation gave potential up scaled yields (tonne/ha) and gross margins (AUD$/ha) of 17% and 33% above the baseline, respectively. In 2030 and at Australian wheatbelt level, climate change impact projected to decline wheat yield by 1%. For 2030, national wheat yields were simulated to decrease yields by 1% when using existing technology and practices but increase them by 18% assuming optimal adaptation. Hence, nationally at 2030 for a fully-adapted wheat system, yield increased by 1% and gross margin by 0.3% compared to the fully adapted current climate baseline. However, there was substantial regional variation with median yields and gross margins decreasing in 55% of sites. Full adaptation of farm systems under current climate is not expected, and so this will remain an on-going challenge. However, by 2030 there will be a greater opportunity to increase the overall water use and nitrogen efficiencies of the Australian wheat belt, mostly resulting from elevated atmospheric CO 2 concentrations. [ABSTRACT FROM AUTHOR]

The annual net primary production (ANPP) of temperate grasslands and production of livestock industries is predicted to decrease in southern Australia with future climate change. By using biophysical modelling, we address productivity and profitability of grazing systems while considering systemic combination of grassland management and animal genetic improvement options. Single incremental adaptations will not completely avert declines in productivity and profitability; hence, combinations of adaptations are needed. The synergistic effects of these adaptations could potentially offset decreasing production and profit in 2030 over the majority of southern Australia, but not in some drier regions after 2030. These results demonstrate the need for changes in strategies over time with greater complexity of adaptations in drier regions. Upscaling over all southern Australia, financially optimal systemic combination (fully enhanced systems) could increase profit by 68.61%, 68.63% and 50.81% in 2030, 2050, and 2070, compared to the production of the historical period with current farm system management. Financially-motivated changes to grazing systems will result in improvement in grassland health, soil environment, and water use efficiency. However, full adaption of systemic adaptation will lead to greater ruminant CH4 emission from 70?kg ha-1?yr-1 in baseline (1970-1999) to 84, 83, and 75?kg ha-1?yr-1 in 2030, 2050, and 2070. Higher rates of CH4 emissions may affect profitability depending on future emissions pricing. In most of the drier regions, greater input intensity and management complexity may be required which requirement is likely to increase over time. However some of the drier regions would still require transformative adaptations. [ABSTRACT FROM AUTHOR]

Climate change is predicted to reduce the productivity of the broadacre livestock industries across southern Australia; to date there has been no formal evaluation of the potential of genetic improvement in cattle or sheep to ameliorate the impacts of changing climates. We used the GRAZPLAN simulation models to assess selection of five traits of sheep and cattle as adaptation options under the SRES A2 global change scenario. Analysis of the breeding strategies was carried out for 25 representative locations, five livestock enterprises and three future years (2030, 2050, 2070). Uncertainty in future climates was taken into account by considering projected climates from four global circulation models. For three sheep enterprises, breeding for greater fleece growth (at constant body size) was predicted to produce the greatest improvements in forage conversion efficiency, and so it was the most effective genetic adaptation option. For beef cow and steer enterprises, breeding for larger body size was most effective; for beef cows, however, this conclusion relied on per-animal costs (including provision of bulls) remaining stable as body size increases. Increased conception rates proved to be less effective but potentially viable as an adaptation in beef cow and crossbred ewe enterprises. In the southern Australian environments that were analysed, our modelling suggests that breeding for tolerance to heat stress is unlikely to improve the performance of livestock production systems even at 2070. Genetic improvement of livestock was able to recover much less of the impact of climate change on profitability at drier locations where the need for adaptation is likely to be greatest. Combinations of feedbase and livestock genetic adaptations are likely to complement one another as the former alter the amount of forage that can be consumed, while the latter affect the efficiency with which consumed forage is converted to animal products. Climate change impacts on pasture production across southern Australia are likely to have only small effects on methane emissions intensity, as are a range of candidate genetic and feedbase adaptations to climate change; methane emissions per hectare in future climates will therefore be driven mainly by changes in livestock numbers due to alterations in pasture productivity. Increasing the forage conversion efficiency of livestock is a possible response to reduced forage supply due to changing climates across southern Australia. Modelling analyses indicate that breeding for greater fleece growth in sheep and for larger body size in cattle are effective genetic adaptation options; increasing conception rates was less effective. Genetic improvement of livestock was less effective at drier locations where the need for adaptation is likely to be greatest. [ABSTRACT FROM AUTHOR]

Broadacre livestock production is a major but highly diverse component of agriculture in Australia that will be significantly exposed to predicted changes in climate over coming decades. We used the GRAZPLAN simulation models to assess the impacts of climate change under the SRES A2 scenario across southern Australia. Climate change impacts were examined across space (25 representative locations) and time (1970-99, 2030, 2050 and 2070 climate) for each of five livestock enterprises. Climate projection uncertainty was considered by analysing projections from four global circulation models ( GCMs). Livestock production scenarios were compared at their profit-maximizing stocking rate, constrained to ensure that risks of soil erosion were acceptable. Impacts on net primary productivity ( ANPP) varied widely between GCM projections; the average declines from historical climate were 9% in 2030, 7% in 2050 and 14% in 2070. Declines in ANPP were larger at lower-rainfall locations. Sensitivity of ANPP to changes in rainfall ranged from 0.4 to 1.7, to temperature increase from −0.15 to +0.07 °C−1 and to CO2 increase from 0.11 to 0.32. At most locations the dry summer period lengthened, exacerbating the greater erosion risk due to lower ANPP. Transpiration efficiency of pastures increased by 6-25%, but the proportion of ANPP that could safely be consumed by livestock fell sharply so that operating profit (at constant prices) fell by an average of 27% in 2030, 32% in 2050 and 48% in 2070. This amplification of ANPP reductions into larger profitability declines is likely to generalize to other extensive livestock systems. Profit declines were most marked at drier locations, with operating losses expected at 9 of the 25 locations by 2070. Differences between livestock enterprises were smaller than differences between locations and dates. Future research into climate change impacts on Australian livestock production needs to emphasise the dry margin of the cereal-livestock zone. [ABSTRACT FROM AUTHOR]

Abstract: The contributions and relationships of erosion by splash and overland flow over a steep slope in a Japanese beech forest in plots with different percentages of ground cover were examined. Three erosion plots (2m wide×5m long) with average understory coverage of 1%, 45%, and 94% were installed. Sediment transported by rain splash and by overland flow was sampled separately. For the plots with sparse, moderate, and high understory coverage, the average proportions of splash soil to total soil erosion during the monitoring period were 16%, 32%, and 18%, respectively. A significant correlation between the amount of splash soil and precipitation was found in the plots with 1% and 45% understory coverage, whereas no statistical relationship was identified for the plot with high understory coverage. At the sparse ground cover plot showing the largest sediment movement, the contribution of splash transport decreased with increasing precipitation. The amount of sheetwash erosion was significantly correlated with the amount of splash soil under the condition of sparse ground cover. This relationship was more pronounced during high precipitation events and the rainy season. Splash contribution to the sediment transport was in the range of 0.8%–76.7%, 2.8%–81% and 2.1%–60.8% for plot with high, moderate and low ground cover, respectively. The sparse ground cover showed the largest variation of splash and sheetwash contribution in soil erosion. This variability was due to variation in ground cover and soil surface wetness condition which led to a variation of detachment and non-linear relationship of sheetwash splash. [Copyright &y& Elsevier]

Australian and Queensland Government's Reef 2050 Water Quality Improvement Plan has set targets for improving the water quality entering the Great Barrier Reef lagoon. Given the large public investment and the deficit of data linking on-farm land management to changes in environmental outcomes, there is a need for a robust and efficient methods of quantifying links between land management and water quality. This paper explores a pragmatic approach to making this link using available data. We demonstrate that a simple parameterisation process is suitable for estimating hydrology and water quality across a wide range of land uses and management practices in agricultural landscapes. However, a manually calibrated model may still require the analysis of parameters to reduce error variances and evaluate uncertainties. Confidence in estimating hydrology and water quality in descending order is: runoff, sediment, nitrogen, phosphorous, and pesticide losses, reflecting the availability of data and inherent error propagation. • A pragmatic modelling by Howleaky is suitable to link management to water quality. • A manually calibrated model may still require a reduction in error variances. • Data availability and inherent error propagation determined confidence in modelling. [ABSTRACT FROM AUTHOR]

Mixed crop-livestock farming systems provide food for over half of the global population. However, some important food exporting countries, like Australia, are predicted to be vulnerable to climate change and may require transformative adaptations if they are to continue their role in food exportation. This paper assesses the potential impacts of projected climate change by 2030 (0.4–1.6° increase in mean temperature) on Australian mixed crop-livestock systems and examines the consequences of shifts in land allocations to cropping and grazing, in these systems, as an adaptation option. Farm bio-economic simulation models were developed for these mixed enterprise systems in several regions of Australia. These models were based on biophysically coupled crop, pasture, and livestock simulation models that in turn drew on site-based downscaled climate projection datasets. The farm models calculated farm profitability and risk measures. A range of land use changes was investigated. At drier locations facing adverse climate change, results showed a transition towards a greater emphasis on livestock production could be beneficial when assessed against multiple criteria of farm profit, downside financial risk, and environmental damage. We highlight some industry and government actions and policies that could facilitate these preferred adaptation strategies at such locations. • Temperature increase of 0.4–1.6° affect mixed crop-livestock systems in Australia. • Transition towards a greater emphasis on livestock production is often desirable. • Financially optimal land allocations vary between historical and future climate. • Increase in the land devoted to pasture is a strategy to manage future climate risk. [ABSTRACT FROM AUTHOR]

Future soil moisture (SM) estimation is a practically useful task for eco-hydrologists, agriculturists, and stakeholders in environment health monitoring to generate comprehensive understanding of hydro-physical and soil dynamic system. This paper demonstrates the capability of a hybridised long short-term memory (LSTM) predictive framework to emulate SM under global warming scenarios. The proposed model is developed by integrating Boruta-random forest (BRF) feature selection and capturing significant antecedent memory of SM behaviour were applied to estimate the future SM using Coupled Model Intercomparison Phase-5 (CMIP5) repository. The BRF is adapted to extract pertinent features in hydro-meteorological variables intrinsically related to SM, and therefore, is used to construct a hybridised deep learning (i.e., BRF-LSTM) model. To establish the viability of deep learning model for SM estimation until 2100, five stations closely matched to the global climate model grid are selected in Australia's Murray Darling Basin. The performance skill of BRF-LSTM model is compared against standalone models (i.e., LSTM, SVR, and MARS). The results showed that the hybrid deep learning model (i.e., BRF-LSTM) with a feature selection capability could significantly outperform the standalone models for both warming simulations. The proposed hybrid model also demonstrated superiority in SM estimation with over 95% of all predictive errors lying below 0.02 mm, and low relative root means square error (≈ 1.06% for RCP4.5 and ≈ 1.888% for RCP8.5) to outperform all the benchmark models. This study demonstrates the capability of LSTM algorithm coupled with BRF feature selection to simulate future soil moisture under climate change, and so, can be successfully implemented in hydrology, agriculture, soil use management and environmental management. [ABSTRACT FROM AUTHOR]

Heat stress is usually assessed using thermal comfort indices (TCIs) that calculate integrated values of temperature, humidity, wind speed and solar radiation. However, the negative effect of heat stress is related not only to the intensity but also the duration of heat stress endured, as well as the accumulated influence from previous time periods. This study was conducted to develop adjusted TCIs which could simultaneously quantify the intensity and duration of heat stress. The data for this study came from production and climate data collected on a robotically milked dairy-farm. Thresholds of heat stress under diurnal pattern (0–24 h) and lag pattern (−90 to 0 d) for different TCIs were identified to be related to a significant decrease of daily milk yields (DMY). An intensity duration index (IDI) was proposed to evaluate daily short-term heat stress (HIDI) and heat stress relief (RIDI), by multiplying the percentage difference between TCIs and their threshold values (i.e. intensity) by the duration. Thresholds of HIDI and RIDI, as well as their sum i.e. IDI total were identified to describe multiple levels of heat stress with different significant decrease rate of DMY from −0.01 to −0.05 kg∙cow−1∙d−1[DMY]∙(%∙h)−1[IDI]. To evaluate the long-term lag and cumulative effects of heat stress, TCIs with weighted cumulative adjustment (TCI WCE) and heat stress adjustment (TCI HS) were defined by assigning a different level of importance to daily TCIs of the previous period and calculating the average of these weighted TCIs. Multiple linear regressions between DMY and adjusted TCIs (i.e. TCI WCE and TCI HS) were performed considering age, body mass (BM) and days in milk (DIM) as basic independent variables. The adjusted R squared (R2) and residual root mean square (RMS) values of these regressions were used for comparison. Using adjustment TCI WCE or TCI HS was found to increase the adjusted R2 and decrease RSS, indicating an improved explanation of variance in heat stress impact. • Intensity and duration index for assessing daily heat stress was developed. • Heat stress and relief of heat stress were evaluated with thresholds identified. • Adjustments of TCIs were created for quantifying lag and cumulative effect. • Using temperature and THI to quantify time-related heat stress were compared. [ABSTRACT FROM AUTHOR]

Thresholds of heat stress are identified by determining the values of thermal comfort indices with significant change of animal responses. However, published thresholds may lead to inaccuracy when dealing with specific climate conditions, animal breeds and production factors. Thus, determining dynamic thresholds might provide better assessment of heat stress, with self-calibration capabilities. In this study, a large dataset of individual age, body mass (BM), days in milk (DIM), daily milk yield (DMY) and milk temperature (MT) of 126 lactating Holstein cows was collected from a robotic dairy farm over five years. The ambient temperature data was collected from a local weather station and processed as daily minimum and mean temperature (T min and T mean). For the whole herd, a new series of heat stress thresholds with stages were defined as comfort stage, milk heat stress, effective heat stress and critical heat stress. The definition was based on the cow's responses in DMY and MT, which provides a potential approach to accurately alert for heat stress in robotic farming systems by using the existing data source. For the specific individuals, dynamic thresholds of heat stress were identified and categorised using the decision tree machine learning model. The categorisation achieved 79–94% overall accuracy, and demonstrated the importance of cooling cows during their early lactation period. • Use broken-line regression to assess cow's heat stress link to production factors. • Decision tree model to choose dynamic threshold of heat stress for individual cow. • Identify multi-thresholds indicating none, mild, effective and critical heat stress. • Demonstrate the importance of cooling cows during early lactation stage. [ABSTRACT FROM AUTHOR]

Robotic milking systems (RMS) have been demonstrated to reduce on-farm labour requirements and collect significant individual-level data in relation to animal health, welfare and production, but they are still largely underutilised. Studies on the relationship between heat stress, animal behaviour and robotic milking performance in a RMS are still insufficient. To model such a relationship, this study focused on analysing the data collected from a RMS system. Animal response indicators of heat stress assessment were rumination time (RT), milk temperature (MT) and daily milk yield (DMY). In addition, RMS milking behaviour, i.e. time of milking (TM), milking frequency (MF), milking duration (MD), milking speed (MS) and milk yield per milking (MY) were also monitored. A new index of rumination efficiency (REI) was created to evaluate rumination efficiency under heat stress, defined as the ratio between DMY and RT. Using multiple broken-line regression, it was found that a 1 °C rise in daily mean temperature could reduce RT by 5.12 min, decrease REI by 0.07 kg·cow−1·h−1, and increase low efficiency milking by 1%. Moreover, the study also found cows prefer to milk between 7:00–9:00AM, and 86% of milking events happened during this period. No significant correlation was found between heat stress and milking behaviour. However, delaying the first milking event of the day and controlling milking intervals to <4 h, was beneficial for REI and robotic milking performance. • Measure rumination efficiency using robotic dairy farming facilities. • Define new index to evaluate heat stress in robotic milking system. • Find cows have no adopted milking behaviour against heat stress. • Determine the decline of robotic milking performance under heat stress. • Modified milking arrangement was recommended with estimated financial benefit. [ABSTRACT FROM AUTHOR]

Thermal comfort indices (TCIs) have been developed to assess heat stress and model the relationship between thermal parameters (e.g. dry-bulb temperature) and animal responses (e.g. daily milk yield, DMY). The published models typically include temperature humidity index (THI), black globe humidity index, environmental stress index, equivalent temperature index, heat load index, respiration rate index and comprehensive climate index. This study was conducted to compare the performance of these published TCIs using data collected from a robotic farm situated in a subtropical climate region. The comparison also included models formulated between basic thermal parameters and animal responses (DMY and milk temperature (MT)). The statistical analyses found dry-bulb temperature can provide a similar level of performance to other TCIs in assessing heat stress. The spatial variability between on-farm measurements and the local weather station can be neglected when modelling with TCIs and MT. For cows with an average DMY of 31 kg cow−1 d−1, the threshold for significant decline of DMY was reported as THI >64 (P < 0.05). The daily minimum TCIs were found to be highly correlated with production loss, indicating that sufficient night-time cooling was important for preventing production losses. The potential of implementing a simplified assessment of heat stress using an on-line dataset was also demonstrated by this study. • Performance evaluation of published TCIs and basic thermal indicators. • Test the consistency of using on-farm microclimate and regional climate data. • THI-64 was found as the start of heat stress for cows with 31 kg·cow−1·d−1 DMY. • Importance of night-time cooling to relief heat stress was demonstrated. [ABSTRACT FROM AUTHOR]

[Display omitted] • We built hybrid Long Short-Term Memory model for Pan Evaporation (E p). • We adopt Neighbourhood Component Analysis for feature selection. • We predict E p in drought-prone Queensland with satellite predictor variables. • Our NCA-LSTM model is compared with competitive benchmark models. • NCA-LSTM model is useful for estimation of evaporative water losses. Evaporation, as a core process within the global hydrological cycle, requires reliable methods to monitor its variation, for decision-making in agriculture, irrigation systems and dam operations, also in other areas of hydrology and water resource management. Accurate monitoring of pan evaporation (E p) is one the most popular approaches to understand the evaporative process. This work aims to construct a hybrid Long Short-Term Memory (LSTM) predictive model that is coupled with Neighbourhood Component Analysis for feature selection to predict E p in drought-prone regions in Queensland, Australia (Amberley, Gatton, Oakey, & Townsville). Utilizing the daily-scale dataset [31 August 2002 to 22 September 2020], the performance of the proposed deep learning (DL) hybrid model, denoted as NCA-LSTM, is compared with competitive benchmark models, i.e., standalone LSTM, other types of DL, single hidden layer neuronal architecture and decision tree-based method. The testing results reveal the lowest Relative Root Mean Square Error ≤ 20 % , Absolute Percentage Bias ≤ 14.5 % and the highest Kling-Gupta Efficiency ≥ 87 % attained by the NCA-LSTM hybrid model (relative to benchmark models) tested for Amberley, Gatton, and Oakey sites. In respect to the predictive efficiency, the proposed NCA-LSTM hybrid model, improved with feature selection, outperforms all benchmark models, indicating its future utility in the prediction of daily E p. In practical sense, the predictive model developed for E p estimation provides an accurate estimation of evaporative water loss in hydrological cycle and therefore, can be implemented in areas of irrigation management, planning of irrigation-based agriculture, and mitigation of financial losses to agricultural and related sectors where, regular monitoring and forecasting of water resources are a vital part of sustainable livelihood and business. [ABSTRACT FROM AUTHOR]

Reference crop evapotranspiration (ETo) is an integral hydrological factor in soil–plant-atmospheric water balance studies and the management of drought events. This paper proposes a new hybrid-deep learning approach, combining convolutional neural network (CNN) and gated recurrent unit (GRU) along with Ant Colony Optimization (ACO), for a multi-step (week 1 to 4) daily-ETo forecast. The method also assimilates a comprehensive dataset with 52 diverse predictors, i.e., satellite-derived moderate resolution imaging spectroradiometer, ground-based datasets from scientific information for landowners and synoptic-scale climate indices. To develop a vigorous CNN-GRU model, a feature selection stage entails the ant colony optimization method implemented to improve the ETo forecast model for the three selected sites in Australian Murray Darling Basin. The results demonstrate excellent forecasting capability of the hybrid CNN-GRU model against the counterpart benchmark models, evidenced by a relatively small mean absolute error and high efficiency. Overall, this study shows that the proposed hybrid CNN-GRU model successfully apprehends the complex and non-linear relationships between predictor variables and the daily ETo. [ABSTRACT FROM AUTHOR]

Heat stress is a significant challenge in dairy farming systems. Dairy cows under heat stress will encounter impaired welfare leading to production losses. As the frequency and magnitude of heat stress events increase in the coming decades, a focus on heat stress reduction studies becomes important. Modelling and on-farm experiments have been used to assess the effects of heat stress on livestock over the last few decades. Mitigation solutions including optimal shed structure, ventilation, feeding regimes, farm management and genetic selection have all been explored. However, under different farm conditions, the heat tolerance and coping ability of dairy cows can vary significantly. Until now, the results from different mathematical models have provided a variety of heat stress thresholds for on-farm use. In practice, it is still costly to determine an accurate heat stress level in order to identify the mitigation requirements. This review summarises previous studies on the effects of heat stress on intensively reared dairy cows and different mitigation approaches. We have undertaken a comparative analysis of thermal indices, animal responses, and mitigation approaches. Recommendations are then given for developing a framework to enhance the measurement, assessment and mitigation of heat stress. Robust monitoring systems, big data analyses and artificial intelligence algorithms are needed for the future development of dynamic, self-calibrating model-based systems, which could provide real-time assessment and minimisation of heat stress. • Devices for monitoring heat stress on cattle are assessed including IOT functions. • Complexity and inconsistency limit the usage of published thermal comfort index. • Fans plus misters are still the most cost effective heat stress mitigation approach. • Conceptual model for developing a globalised framework is proposed. [ABSTRACT FROM AUTHOR]

This study aimed to examine flood hazard zoning and assess the role of check dams as effective hydraulic structures in reducing flood hazards. To this end, factors associated with topographic, hydrologic and human characteristics were used to develop indices for flood mapping and assessment. These indices and their components were weighed for flood hazard zoning using two methods: (i) a multi-criterion decision-making model in fuzzy logic and (ii) entropy weight. After preparing the flood hazard map by using the above indices and methods, the characteristics of the change‐point were used to assess the role of the check dams in reducing flood risk. The method was used in the Ilanlu catchment, located in the northwest of Hamadan province, Iran, where it is prone to frequent flood events. The results showed that the area of 'very low', 'low' and 'moderate' flood hazard zones increased from about 2.2% to 7.3%, 8.6% to 19.6% and 22.7% to 31.2% after the construction of check dams, respectively. Moreover, the area of 'high' and 'very high' flood hazard zones decreased from 39.8% to 29.6%, and 26.7% to 12.2%, respectively. [ABSTRACT FROM AUTHOR]

Calibration, the estimation of model parameters based on fitting the model to experimental data, is among the first steps in many applications of process-based models and has an important impact on simulated values. We propose a novel method of developing guidelines for calibration of process-based models, based on development of recommendations for calibration of the phenology component of crop models. The approach was based on a multi-model study, where all teams were provided with the same data and asked to return simulations for the same conditions. All teams were asked to document in detail their calibration approach, including choices with respect to criteria for best parameters, choice of parameters to estimate and software. Based on an analysis of the advantages and disadvantages of the various choices, we propose calibration recommendations that cover a comprehensive list of decisions and that are based on actual practices. • We propose a new approach to calibration recommendations for process-based models. • Approach is based on analyzing calibration in multi-model simulation exercises. • Resulting recommendations are holistic and anchored in actual practice. • We derive calibration recommendations for crop models used to simulate phenology. • Recommendations concern: objective function, parameters to estimate, software used. [ABSTRACT FROM AUTHOR]

Land application of alkaline irrigation water is an increasing practice in most agricultural lands around the world due to the shortage of freshwater resources. Accurate evaluation of the effects of alkalinity on soil properties is essential to avoid environmental risks. In this study, we used long leaching columns to evaluate alkalinisation and sodification hazards in soils in the laboratory at different water qualities (0, 100, 310 and 650 HCO 3 -, mg L−1) with electrical conductivity (EC) ≈ 2.1 dS m−1 and sodium adsorption ratio (SAR) ≈ 12 (mmol c L−1)0.5. The ability of the HYDRUS-1D model to simulate solute and water movement under unsaturated conditions in columns of 40 cm height filled with acidic, neutral or alkaline soils was also assessed. Changes in soil EC, SAR, pH and alkalinity were monitored at 5, 15, 25 and 35 cm depths for 290 days. Increased solution alkalinity resulted in increased pH, alkalinity and sodicity within the soil profile, in particular for the soil surface and acidic soils. In general, the HYDRUS model, using the standard hydraulic reduction scaling factor, was able to simulate the effects of alkalinity in the soil profile and the associated hydraulic conductivity reduction. Amending the pH driven hydraulic reduction scaling factor in the model to a non-linear, soil-specific, pedotransfer function significantly improved the correlation between predicted and observed hydraulic conductivity. The findings of this study provide validation for a non-linear approach towards determining the pH hydraulic reduction scaling factor in the HYDRUS-1D model for unsaturated conditions. However, it is noted that further improvement of this non-linear approach is required to incorporate other factors governing soil structural stability. • The pedotransfer hydraulic reduction function significantly improves hydraulic reduction prediction. • The pH and alkalinity (HCO 3 -) are the primary drivers of model variability. • The current standard hydraulic conductivity reduction in HYDRUS model requires improvement. [ABSTRACT FROM AUTHOR]

Modelling workflow for BRF-LSTM and BRF-GRU predictive models. [Display omitted] • Deep learning hybrid predictive model (BRF-LSTM) is built for streamflow forecasting. • Climate indices, rainfall and periodicity are factored for accurate predictions. • Adopts feature algorithm (i.e. Boruta) with long short-term memory and gated recurrent unit. • Six gauging sites tested; BRF-LSTM yields > 98% errors in ± 0.015 m, ~1.30% relative error. • The proposed model is useful for hydrological and strategic water resources planning. Long-term forecasting of any hydrologic phenomena is essential for strategic environmental planning, hydrologic and other forms of structural design, agriculture, and water resources management. Climate mode indices, utilising machine learning methods, are frequently considered as predictor variables in order to forecast several different hydrological variables. In this study, a feature selection algorithm based on two different deep learning models, i.e., long short-term memory and a gated recurrent unit, is applied to improve the forecasting capability of streamflow water levels at six gauging stations in the Murray Darling Basin of Australia. This paper therefore aggregates the significant antecedent lag memory of climate mode indices, rainfall, and the monthly factor based on the periodicity as the predictor variables to attain significantly accurate stream water level forecasts. This novel method identifies an improved relationship between the stream water level and climate mode indices through the aggregation of the significant lagged datasets capturing the historical features to predict the future streamflow water level. The boruta feature selection algorithm (BRF) was then applied in a two phase process before and after attaining the significant lagged inputs to screen the optimum predictor variables. The merits of the forecast models were evaluated through different performance evaluation criteria. The results show that the accumulated significant lagged inputs based on climate mode indices, along with the rainfall and periodicity factors are seen to provide improved forecasting of the SWL over the non-BRF deep learning approaches where no prior feature selection was applied. The hybrid LSTM method (i.e., BRF-LSTM model) achieved a unique advantage in terms of SWL forecasting, particularly attaining over 98% of the predictive errors lying within a band of +/-0.015 m with relatively low relative errors (RRMSE ≈1.30% and RMAE ≈ 0.882%), outperforming all of the benchmark models. It is also found that the periodicity factor has a potential influence on the accuracy of the forecast models for the four monitored study stations. This study concludes that the newly developed hybrid deep learning approaches, coupled with the BRF feature selection, provide improved forecasting performance. The hybrid approach developed in this paper can therefore be used to provide a strong provide predictive response algorithm for the hydrological variables that were influenced by the low-frequency variability of the climate model indices in respect to streamflow water level. [ABSTRACT FROM AUTHOR]

• 27 modeling groups were evaluated for wheat phenology predictions for France. • Calibration and evaluation data were sampled from the same target population. • The calibration and evaluation data have neither year nor site in common. • The best groups had a mean absolute error comparable to the measurement error. • Model structure alone does not determine prediction accuracy. Predicting phenology is essential for adapting varieties to different environmental conditions and for crop management. Therefore, it is important to evaluate how well different crop modeling groups can predict phenology. Multiple evaluation studies have been previously published, but it is still difficult to generalize the findings from such studies since they often test some specific aspect of extrapolation to new conditions, or do not test on data that is truly independent of the data used for calibration. In this study, we analyzed the prediction of wheat phenology in Northern France under observed weather and current management, which is a problem of practical importance for wheat management. The results of 27 modeling groups are evaluated, where modeling group encompasses model structure, i.e. the model equations, the calibration method and the values of those parameters not affected by calibration. The data for calibration and evaluation are sampled from the same target population, thus extrapolation is limited. The calibration and evaluation data have neither year nor site in common, to guarantee rigorous evaluation of prediction for new weather and sites. The best modeling groups, and also the mean and median of the simulations, have a mean absolute error (MAE) of about 3 days, which is comparable to the measurement error. Almost all models do better than using average number of days or average sum of degree days to predict phenology. On the other hand, there are important differences between modeling groups, due to model structural differences and to differences between groups using the same model structure, which emphasizes that model structure alone does not completely determine prediction accuracy. In addition to providing information for our specific environments and varieties, these results are a useful contribution to a knowledge base of how well modeling groups can predict phenology, when provided with calibration data from the target population. [ABSTRACT FROM AUTHOR]

Remotely sensed soil moisture forecasting through satellite-based sensors to estimate the future state of the underlying soils plays a critical role in planning and managing water resources and sustainable agricultural practices. In this paper, Deep Learning (DL) hybrid models (i.e., CEEMDAN-CNN-GRU) are designed for daily time-step surface soil moisture (SSM) forecasts, employing the gated recurrent unit (GRU), complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), and convolutional neural network (CNN). To establish the objective model's viability for SSM forecasting at multi-step daily horizons, the hybrid CEEMDAN-CNN-GRU model is tested at 1st, 5th, 7th, 14th, 21st, and 30th day ahead period by assimilating a comprehensive pool of 52 predictor dataset obtained from three distinct data sources. Data comprise satellite-derived Global Land Data Assimilation System (GLDAS) repository a global, high-temporal resolution, unique terrestrial modelling system, and ground-based variables from Scientific Information Landowners (SILO) and synoptic-scale climate indices. The results demonstrate the forecasting capability of the hybrid CEEMDAN-CNN-GRU model with respect to the counterpart comparative models. This is supported by a relatively lower value of the mean absolute percentage and root mean square error. In terms of the statistical score metrics and infographics employed to test the final model's utility, the proposed CEEMDAN-CNN-GRU models are considerably superior compared to a standalone and other hybrid method tested on independent SSM data developed through feature selection approaches. Thus, the proposed approach can be successfully implemented in hydrology and agriculture management. [ABSTRACT FROM AUTHOR]