---

 Although, weed control in saffron farms is critical, no herbicide is registered for saffron fields. This experiment was carried out in a randomized complete block design with three replicates during 2016-2017. Treatments included application of trifluralin, pendimethalin, metribuzin, bentazon, ioxynil, oxadiazon, oxyfluorfen, haloxyfop-r-methyl, sethoxydim, clethodim, cycloxydim, nicosulfuron, rimsulfuron, tribenuron methyl, foramsulfuron, paraquat, dicamba + triasulfuron, and dicamba + tritosulfuron herbicides at recommended and reduced doses. Mother corms were planted on 10th of September 2016 at 5 × 10 cm corms distance and planting depth of 15 cm. Measured indices included: number of flowers, fresh and dry weights of flower and stigma, number of replacement corms and total corms weight. Results showed that visual phytotoxic symptoms were not observed in pre emergence herbicides. Post emergence herbicides showed different levels of phytotoxicity from slight to severe. The application of paraquat, oxyfluorfen and oxadiazon, caused higher levels of phytotoxicity compared to other herbicides. Acetyl CoA carboxylase inhibitor herbicides caused the least injury to saffron, while acetolactate synthase inhibitor herbicides damaged saffron severely. The highest and the lowest dried stigma yield was obtained from control treatment (0.54 g.m^-2) and post application of tribenuron methyl (0.003 g.m^-2) respectively. Among pre emergence herbicides, the highest dried stigma yield was recorded for pendimethalin herbicide. The post application of metribuzin, oxadiazone and oxyfluorfen resulted in greater dried stigma yield than other broadleaf herbicides. By reducing herbicide dose saffron yield increased and phytotoxic levels were reduced significantly. Among the studied herbicides, trifluralin, oxyfluorfen, pendimethalin and metribuzin can be used as selected herbicides in saffron.
 

---

Estimating the spatial distribution of weeds for site-specific control is essential. Therefore, this research was conducted to predict and interpolate the spatial distribution of Amaranthus retroflexus L. populations using a Radial Basis Function Neural Network (RBF-NN) in two potato fields. Weed population data were collected from sampling 200 and 36 points, respectively, in two commercial potato fields in Jolge Rokh, of Torbat Heidarieh in Khorasan Razavi and Mojen of Shahroud in Semnan Provinces, Iran, in 2012. Some statistical tests, such as comparisons of the means, variance and statistical distribution, as well as linear regression, were used for the observed point sample data and the estimated weed seedling density surfaces to evaluate the neural network capability for predicting the spatial distribution of the weed. The results showed that the trained RBF-NN had high capability in the spatial prediction in points that were not sampled with 100% output, 0.999 coefficients, and an average error of less than 0.04 and 0.07 in the Mojen and Jolge Rokh Regions, respectively. Test results also showed that there was no significant difference between the statistical characteristics of actual data and the values predicted by the RBF-NN. According to the experimental results, the RBF-NN can be used as an alternative method to estimate the spatial changes function of annual weeds with random dispersion, such as Redroot Pigweed.