No abstract

Changes in milk production associated with occurrence of clinical diseases (dystocia, stillbirth, twin births, milk fever, retained placenta, displaced abomasum, limping due to foot lesions, metritis, ketosis, and mastitis) were investigated. Data were collected daily on 388 lactation. Stepwise least squares regression was used to evaluate existence of associations between diseases and six yield measures that characterized milk production in the first 119 d postpartum. Logistic regression was used to investigate whether milk yield 1 to 5 d in milk might be of use to detect cows with early postpartum metritis (less than 21 d after calving). Lower milk production to 5 d postpartum was associated with an increased risk of early postpartum metritis in the logistic regression model. Yield to 5 and to 21 d postpartum was lower in cases of stillbirth, retained placenta, and early postpartum metritis. Yield from 22 to 49 d postpartum remained lower in cows diagnosed with early postpartum metritis. Milk yield losses occurred during diagnosis and treatment of displaced abomasum and mastitis. Ketosis was associated with yield losses prior to and at treatment. Ketosis to 21 d in milk was also associated with lower production after treatment. Limping diagnosed in the first 49 d postpartum coincided with higher yield to 5 d, to 21 d, and after 49 d postpartum.

Lake Water Surface Area (WSA) plays a vital role in environmental preservation and future water resource planning and management. Accurately mapping, monitoring and forecasting Lake WSA changes are of great importance to regulatory agencies. This study used the MODIS satellite images to extract a monthly time series of WSA of two lakes located in Iran from 2001 to 2019. Following a consequence of image and time series preprocessing to obtain the preprocessed lake surface area time series, the outcomes were modeled by the Long-Short-Term Memory (LSTM) deep learning (DL) method, the stochastic Seasonal Auto-Regressive Integrated Moving Average (SARIMA) method and hybridization of these two techniques with the objective of developing WSA forecasts. After separate standardization and normalization of AL TS and reevaluation of the preprocessed data, the SARIMA (1, 0, 0) (0, 1, 1)12 model outperformed sole LSTM models with correlation index of (R) 0.819, mean absolute error (MAE) of 49.425 and mean absolute percentage error (MAPE) of 0.106. On the other hand, the hybridization (stochastic-DL) enhanced the reproduction of the primal statistical properties of WSA data and caused better mediation. However, the other accuracy indices did not change markedly (R 0.819, MAE 49.310, MAPE 0.105). The multi-step preprocessing and reevaluation also caused all LSTM models to produce their best results by less than 12 inputs.

No abstract

No abstract